llm-relay 0.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +236 -0
- package/config.example.json +45 -0
- package/dist/anthropic.d.ts +49 -0
- package/dist/anthropic.js +35 -0
- package/dist/anthropic.js.map +1 -0
- package/dist/backend.d.ts +36 -0
- package/dist/backend.js +135 -0
- package/dist/backend.js.map +1 -0
- package/dist/catalog.d.ts +55 -0
- package/dist/catalog.js +148 -0
- package/dist/catalog.js.map +1 -0
- package/dist/cli.d.ts +2 -0
- package/dist/cli.js +137 -0
- package/dist/cli.js.map +1 -0
- package/dist/config.d.ts +88 -0
- package/dist/config.js +248 -0
- package/dist/config.js.map +1 -0
- package/dist/emitSse.d.ts +18 -0
- package/dist/emitSse.js +88 -0
- package/dist/emitSse.js.map +1 -0
- package/dist/log.d.ts +26 -0
- package/dist/log.js +24 -0
- package/dist/log.js.map +1 -0
- package/dist/registry.d.ts +47 -0
- package/dist/registry.js +80 -0
- package/dist/registry.js.map +1 -0
- package/dist/repair.d.ts +24 -0
- package/dist/repair.js +44 -0
- package/dist/repair.js.map +1 -0
- package/dist/reshaper.d.ts +46 -0
- package/dist/reshaper.js +147 -0
- package/dist/reshaper.js.map +1 -0
- package/dist/server.d.ts +9 -0
- package/dist/server.js +619 -0
- package/dist/server.js.map +1 -0
- package/dist/sse.d.ts +2 -0
- package/dist/sse.js +105 -0
- package/dist/sse.js.map +1 -0
- package/dist/validator.d.ts +35 -0
- package/dist/validator.js +126 -0
- package/dist/validator.js.map +1 -0
- package/docs/tier-data.json +4601 -0
- package/package.json +39 -0
|
@@ -0,0 +1,4601 @@
|
|
|
1
|
+
{
|
|
2
|
+
"synced_at": "2026-07-15T05:24:15.477Z",
|
|
3
|
+
"sources": {
|
|
4
|
+
"bfcl": {
|
|
5
|
+
"url": "https://gorilla.cs.berkeley.edu/data_overall.csv",
|
|
6
|
+
"note": "tool-use / function-calling accuracy (primary signal)",
|
|
7
|
+
"model_count": 82
|
|
8
|
+
},
|
|
9
|
+
"lmarena": {
|
|
10
|
+
"url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/main/text_style_control/latest-00000-of-00001.parquet",
|
|
11
|
+
"note": "general capability (secondary)",
|
|
12
|
+
"model_count": 374
|
|
13
|
+
}
|
|
14
|
+
},
|
|
15
|
+
"warnings": [],
|
|
16
|
+
"composite_note": "Rank-normalized mean; BFCL overall weighted 2x (tool-call proxy). Relative only.",
|
|
17
|
+
"models": [
|
|
18
|
+
{
|
|
19
|
+
"name": "claude-fable-5",
|
|
20
|
+
"norm": "claude-fable-5",
|
|
21
|
+
"bfcl_overall": null,
|
|
22
|
+
"bfcl_multi_turn": null,
|
|
23
|
+
"bfcl_irrelevance": null,
|
|
24
|
+
"arena_rating": 1507.5488638129564,
|
|
25
|
+
"arena_rank": 1,
|
|
26
|
+
"composite": 1,
|
|
27
|
+
"composite_rank": 1
|
|
28
|
+
},
|
|
29
|
+
{
|
|
30
|
+
"name": "claude-opus-4-6-thinking",
|
|
31
|
+
"norm": "claude-opus-4-6-thinking",
|
|
32
|
+
"bfcl_overall": null,
|
|
33
|
+
"bfcl_multi_turn": null,
|
|
34
|
+
"bfcl_irrelevance": null,
|
|
35
|
+
"arena_rating": 1503.5867750818463,
|
|
36
|
+
"arena_rank": 2,
|
|
37
|
+
"composite": 0.9973190348525469,
|
|
38
|
+
"composite_rank": 2
|
|
39
|
+
},
|
|
40
|
+
{
|
|
41
|
+
"name": "claude-opus-4-7-thinking",
|
|
42
|
+
"norm": "claude-opus-4-7-thinking",
|
|
43
|
+
"bfcl_overall": null,
|
|
44
|
+
"bfcl_multi_turn": null,
|
|
45
|
+
"bfcl_irrelevance": null,
|
|
46
|
+
"arena_rating": 1502.8963024848595,
|
|
47
|
+
"arena_rank": 3,
|
|
48
|
+
"composite": 0.9946380697050938,
|
|
49
|
+
"composite_rank": 3
|
|
50
|
+
},
|
|
51
|
+
{
|
|
52
|
+
"name": "claude-opus-4-6",
|
|
53
|
+
"norm": "claude-opus-4-6",
|
|
54
|
+
"bfcl_overall": null,
|
|
55
|
+
"bfcl_multi_turn": null,
|
|
56
|
+
"bfcl_irrelevance": null,
|
|
57
|
+
"arena_rating": 1497.7023533941376,
|
|
58
|
+
"arena_rank": 4,
|
|
59
|
+
"composite": 0.9919571045576407,
|
|
60
|
+
"composite_rank": 4
|
|
61
|
+
},
|
|
62
|
+
{
|
|
63
|
+
"name": "claude-opus-4-7",
|
|
64
|
+
"norm": "claude-opus-4-7",
|
|
65
|
+
"bfcl_overall": null,
|
|
66
|
+
"bfcl_multi_turn": null,
|
|
67
|
+
"bfcl_irrelevance": null,
|
|
68
|
+
"arena_rating": 1494.1023688131215,
|
|
69
|
+
"arena_rank": 5,
|
|
70
|
+
"composite": 0.9892761394101877,
|
|
71
|
+
"composite_rank": 5
|
|
72
|
+
},
|
|
73
|
+
{
|
|
74
|
+
"name": "muse-spark-1.1",
|
|
75
|
+
"norm": "muse-spark-1.1",
|
|
76
|
+
"bfcl_overall": null,
|
|
77
|
+
"bfcl_multi_turn": null,
|
|
78
|
+
"bfcl_irrelevance": null,
|
|
79
|
+
"arena_rating": 1491.0229630209024,
|
|
80
|
+
"arena_rank": 6,
|
|
81
|
+
"composite": 0.9865951742627346,
|
|
82
|
+
"composite_rank": 6
|
|
83
|
+
},
|
|
84
|
+
{
|
|
85
|
+
"name": "muse-spark",
|
|
86
|
+
"norm": "muse-spark",
|
|
87
|
+
"bfcl_overall": null,
|
|
88
|
+
"bfcl_multi_turn": null,
|
|
89
|
+
"bfcl_irrelevance": null,
|
|
90
|
+
"arena_rating": 1487.5848626450409,
|
|
91
|
+
"arena_rank": 7,
|
|
92
|
+
"composite": 0.9839142091152815,
|
|
93
|
+
"composite_rank": 7
|
|
94
|
+
},
|
|
95
|
+
{
|
|
96
|
+
"name": "gemini-3.1-pro-preview",
|
|
97
|
+
"norm": "gemini-3.1-pro-preview",
|
|
98
|
+
"bfcl_overall": null,
|
|
99
|
+
"bfcl_multi_turn": null,
|
|
100
|
+
"bfcl_irrelevance": null,
|
|
101
|
+
"arena_rating": 1485.8383930867967,
|
|
102
|
+
"arena_rank": 8,
|
|
103
|
+
"composite": 0.9812332439678284,
|
|
104
|
+
"composite_rank": 8
|
|
105
|
+
},
|
|
106
|
+
{
|
|
107
|
+
"name": "gemini-3-pro",
|
|
108
|
+
"norm": "gemini-3-pro",
|
|
109
|
+
"bfcl_overall": null,
|
|
110
|
+
"bfcl_multi_turn": null,
|
|
111
|
+
"bfcl_irrelevance": null,
|
|
112
|
+
"arena_rating": 1485.780909191792,
|
|
113
|
+
"arena_rank": 9,
|
|
114
|
+
"composite": 0.9785522788203753,
|
|
115
|
+
"composite_rank": 9
|
|
116
|
+
},
|
|
117
|
+
{
|
|
118
|
+
"name": "gpt-5.6-sol-xhigh",
|
|
119
|
+
"norm": "gpt-5.6-sol-xhigh",
|
|
120
|
+
"bfcl_overall": null,
|
|
121
|
+
"bfcl_multi_turn": null,
|
|
122
|
+
"bfcl_irrelevance": null,
|
|
123
|
+
"arena_rating": 1484.3000753737224,
|
|
124
|
+
"arena_rank": 10,
|
|
125
|
+
"composite": 0.9758713136729222,
|
|
126
|
+
"composite_rank": 10
|
|
127
|
+
},
|
|
128
|
+
{
|
|
129
|
+
"name": "claude-opus-4-8-thinking",
|
|
130
|
+
"norm": "claude-opus-4-8-thinking",
|
|
131
|
+
"bfcl_overall": null,
|
|
132
|
+
"bfcl_multi_turn": null,
|
|
133
|
+
"bfcl_irrelevance": null,
|
|
134
|
+
"arena_rating": 1482.5883722382105,
|
|
135
|
+
"arena_rank": 11,
|
|
136
|
+
"composite": 0.9731903485254692,
|
|
137
|
+
"composite_rank": 11
|
|
138
|
+
},
|
|
139
|
+
{
|
|
140
|
+
"name": "gpt-5.5-high",
|
|
141
|
+
"norm": "gpt-5.5-high",
|
|
142
|
+
"bfcl_overall": null,
|
|
143
|
+
"bfcl_multi_turn": null,
|
|
144
|
+
"bfcl_irrelevance": null,
|
|
145
|
+
"arena_rating": 1482.3014458397727,
|
|
146
|
+
"arena_rank": 12,
|
|
147
|
+
"composite": 0.9705093833780161,
|
|
148
|
+
"composite_rank": 12
|
|
149
|
+
},
|
|
150
|
+
{
|
|
151
|
+
"name": "gpt-5.4-high",
|
|
152
|
+
"norm": "gpt-5.4-high",
|
|
153
|
+
"bfcl_overall": null,
|
|
154
|
+
"bfcl_multi_turn": null,
|
|
155
|
+
"bfcl_irrelevance": null,
|
|
156
|
+
"arena_rating": 1476.9018824849136,
|
|
157
|
+
"arena_rank": 13,
|
|
158
|
+
"composite": 0.967828418230563,
|
|
159
|
+
"composite_rank": 13
|
|
160
|
+
},
|
|
161
|
+
{
|
|
162
|
+
"name": "gemini-3.5-flash-high",
|
|
163
|
+
"norm": "gemini-3.5-flash-high",
|
|
164
|
+
"bfcl_overall": null,
|
|
165
|
+
"bfcl_multi_turn": null,
|
|
166
|
+
"bfcl_irrelevance": null,
|
|
167
|
+
"arena_rating": 1476.4394357887702,
|
|
168
|
+
"arena_rank": 14,
|
|
169
|
+
"composite": 0.9651474530831099,
|
|
170
|
+
"composite_rank": 14
|
|
171
|
+
},
|
|
172
|
+
{
|
|
173
|
+
"name": "gpt-5.2-chat-latest-20260210",
|
|
174
|
+
"norm": "gpt-5.2-chat-latest-20260210",
|
|
175
|
+
"bfcl_overall": null,
|
|
176
|
+
"bfcl_multi_turn": null,
|
|
177
|
+
"bfcl_irrelevance": null,
|
|
178
|
+
"arena_rating": 1475.625056957988,
|
|
179
|
+
"arena_rank": 15,
|
|
180
|
+
"composite": 0.9624664879356568,
|
|
181
|
+
"composite_rank": 15
|
|
182
|
+
},
|
|
183
|
+
{
|
|
184
|
+
"name": "qwen3.7-max-preview",
|
|
185
|
+
"norm": "qwen3.7-max-preview",
|
|
186
|
+
"bfcl_overall": null,
|
|
187
|
+
"bfcl_multi_turn": null,
|
|
188
|
+
"bfcl_irrelevance": null,
|
|
189
|
+
"arena_rating": 1475.0112992073477,
|
|
190
|
+
"arena_rank": 16,
|
|
191
|
+
"composite": 0.9597855227882037,
|
|
192
|
+
"composite_rank": 16
|
|
193
|
+
},
|
|
194
|
+
{
|
|
195
|
+
"name": "gemini-3.5-flash-medium",
|
|
196
|
+
"norm": "gemini-3.5-flash-medium",
|
|
197
|
+
"bfcl_overall": null,
|
|
198
|
+
"bfcl_multi_turn": null,
|
|
199
|
+
"bfcl_irrelevance": null,
|
|
200
|
+
"arena_rating": 1474.9738576186428,
|
|
201
|
+
"arena_rank": 17,
|
|
202
|
+
"composite": 0.9571045576407506,
|
|
203
|
+
"composite_rank": 17
|
|
204
|
+
},
|
|
205
|
+
{
|
|
206
|
+
"name": "claude-opus-4-8",
|
|
207
|
+
"norm": "claude-opus-4-8",
|
|
208
|
+
"bfcl_overall": null,
|
|
209
|
+
"bfcl_multi_turn": null,
|
|
210
|
+
"bfcl_irrelevance": null,
|
|
211
|
+
"arena_rating": 1474.929342881376,
|
|
212
|
+
"arena_rank": 18,
|
|
213
|
+
"composite": 0.9544235924932976,
|
|
214
|
+
"composite_rank": 18
|
|
215
|
+
},
|
|
216
|
+
{
|
|
217
|
+
"name": "grok-4.20-beta1",
|
|
218
|
+
"norm": "grok-4.20-beta1",
|
|
219
|
+
"bfcl_overall": null,
|
|
220
|
+
"bfcl_multi_turn": null,
|
|
221
|
+
"bfcl_irrelevance": null,
|
|
222
|
+
"arena_rating": 1474.3209816427993,
|
|
223
|
+
"arena_rank": 19,
|
|
224
|
+
"composite": 0.9517426273458445,
|
|
225
|
+
"composite_rank": 19
|
|
226
|
+
},
|
|
227
|
+
{
|
|
228
|
+
"name": "gpt-5.5",
|
|
229
|
+
"norm": "gpt-5.5",
|
|
230
|
+
"bfcl_overall": null,
|
|
231
|
+
"bfcl_multi_turn": null,
|
|
232
|
+
"bfcl_irrelevance": null,
|
|
233
|
+
"arena_rating": 1474.1636593664164,
|
|
234
|
+
"arena_rank": 20,
|
|
235
|
+
"composite": 0.9490616621983914,
|
|
236
|
+
"composite_rank": 20
|
|
237
|
+
},
|
|
238
|
+
{
|
|
239
|
+
"name": "grok-4.20-beta-0309-reasoning",
|
|
240
|
+
"norm": "grok-4.20-beta-0309-reasoning",
|
|
241
|
+
"bfcl_overall": null,
|
|
242
|
+
"bfcl_multi_turn": null,
|
|
243
|
+
"bfcl_irrelevance": null,
|
|
244
|
+
"arena_rating": 1473.659837732118,
|
|
245
|
+
"arena_rank": 21,
|
|
246
|
+
"composite": 0.9463806970509383,
|
|
247
|
+
"composite_rank": 21
|
|
248
|
+
},
|
|
249
|
+
{
|
|
250
|
+
"name": "gemini-3-flash",
|
|
251
|
+
"norm": "gemini-3-flash",
|
|
252
|
+
"bfcl_overall": null,
|
|
253
|
+
"bfcl_multi_turn": null,
|
|
254
|
+
"bfcl_irrelevance": null,
|
|
255
|
+
"arena_rating": 1473.1902996916317,
|
|
256
|
+
"arena_rank": 22,
|
|
257
|
+
"composite": 0.9436997319034852,
|
|
258
|
+
"composite_rank": 22
|
|
259
|
+
},
|
|
260
|
+
{
|
|
261
|
+
"name": "gpt-5.5-instant",
|
|
262
|
+
"norm": "gpt-5.5-instant",
|
|
263
|
+
"bfcl_overall": null,
|
|
264
|
+
"bfcl_multi_turn": null,
|
|
265
|
+
"bfcl_irrelevance": null,
|
|
266
|
+
"arena_rating": 1473.0451968542677,
|
|
267
|
+
"arena_rank": 23,
|
|
268
|
+
"composite": 0.9410187667560321,
|
|
269
|
+
"composite_rank": 23
|
|
270
|
+
},
|
|
271
|
+
{
|
|
272
|
+
"name": "claude-opus-4-5-20251101-thinking-32k",
|
|
273
|
+
"norm": "claude-opus-4-5-20251101-thinking-32k",
|
|
274
|
+
"bfcl_overall": null,
|
|
275
|
+
"bfcl_multi_turn": null,
|
|
276
|
+
"bfcl_irrelevance": null,
|
|
277
|
+
"arena_rating": 1472.9130074162144,
|
|
278
|
+
"arena_rank": 24,
|
|
279
|
+
"composite": 0.938337801608579,
|
|
280
|
+
"composite_rank": 24
|
|
281
|
+
},
|
|
282
|
+
{
|
|
283
|
+
"name": "glm-5.1",
|
|
284
|
+
"norm": "glm-5.1",
|
|
285
|
+
"bfcl_overall": null,
|
|
286
|
+
"bfcl_multi_turn": null,
|
|
287
|
+
"bfcl_irrelevance": null,
|
|
288
|
+
"arena_rating": 1471.672948071041,
|
|
289
|
+
"arena_rank": 25,
|
|
290
|
+
"composite": 0.935656836461126,
|
|
291
|
+
"composite_rank": 25
|
|
292
|
+
},
|
|
293
|
+
{
|
|
294
|
+
"name": "claude-sonnet-4-6",
|
|
295
|
+
"norm": "claude-sonnet-4-6",
|
|
296
|
+
"bfcl_overall": null,
|
|
297
|
+
"bfcl_multi_turn": null,
|
|
298
|
+
"bfcl_irrelevance": null,
|
|
299
|
+
"arena_rating": 1471.642584607444,
|
|
300
|
+
"arena_rank": 26,
|
|
301
|
+
"composite": 0.9329758713136729,
|
|
302
|
+
"composite_rank": 26
|
|
303
|
+
},
|
|
304
|
+
{
|
|
305
|
+
"name": "grok-4.20-multi-agent-beta-0309",
|
|
306
|
+
"norm": "grok-4.20-multi-agent-beta-0309",
|
|
307
|
+
"bfcl_overall": null,
|
|
308
|
+
"bfcl_multi_turn": null,
|
|
309
|
+
"bfcl_irrelevance": null,
|
|
310
|
+
"arena_rating": 1470.7953882167562,
|
|
311
|
+
"arena_rank": 27,
|
|
312
|
+
"composite": 0.9302949061662198,
|
|
313
|
+
"composite_rank": 27
|
|
314
|
+
},
|
|
315
|
+
{
|
|
316
|
+
"name": "ernie-5.1",
|
|
317
|
+
"norm": "ernie-5.1",
|
|
318
|
+
"bfcl_overall": null,
|
|
319
|
+
"bfcl_multi_turn": null,
|
|
320
|
+
"bfcl_irrelevance": null,
|
|
321
|
+
"arena_rating": 1468.381303007475,
|
|
322
|
+
"arena_rank": 29,
|
|
323
|
+
"composite": 0.9249329758713136,
|
|
324
|
+
"composite_rank": 28
|
|
325
|
+
},
|
|
326
|
+
{
|
|
327
|
+
"name": "grok-4.1-thinking",
|
|
328
|
+
"norm": "grok-4.1-thinking",
|
|
329
|
+
"bfcl_overall": null,
|
|
330
|
+
"bfcl_multi_turn": null,
|
|
331
|
+
"bfcl_irrelevance": null,
|
|
332
|
+
"arena_rating": 1465.917459776027,
|
|
333
|
+
"arena_rank": 30,
|
|
334
|
+
"composite": 0.9222520107238605,
|
|
335
|
+
"composite_rank": 29
|
|
336
|
+
},
|
|
337
|
+
{
|
|
338
|
+
"name": "gpt-5.4",
|
|
339
|
+
"norm": "gpt-5.4",
|
|
340
|
+
"bfcl_overall": null,
|
|
341
|
+
"bfcl_multi_turn": null,
|
|
342
|
+
"bfcl_irrelevance": null,
|
|
343
|
+
"arena_rating": 1465.7187577889533,
|
|
344
|
+
"arena_rank": 31,
|
|
345
|
+
"composite": 0.9195710455764075,
|
|
346
|
+
"composite_rank": 30
|
|
347
|
+
},
|
|
348
|
+
{
|
|
349
|
+
"name": "mimo-v2.5-pro",
|
|
350
|
+
"norm": "mimo-v2.5-pro",
|
|
351
|
+
"bfcl_overall": null,
|
|
352
|
+
"bfcl_multi_turn": null,
|
|
353
|
+
"bfcl_irrelevance": null,
|
|
354
|
+
"arena_rating": 1465.5461098490844,
|
|
355
|
+
"arena_rank": 32,
|
|
356
|
+
"composite": 0.9168900804289544,
|
|
357
|
+
"composite_rank": 31
|
|
358
|
+
},
|
|
359
|
+
{
|
|
360
|
+
"name": "Claude-Sonnet-4-5-20250929 (FC)",
|
|
361
|
+
"norm": "claude-sonnet-4-5-20250929",
|
|
362
|
+
"bfcl_overall": 73.24,
|
|
363
|
+
"bfcl_multi_turn": 61.37,
|
|
364
|
+
"bfcl_irrelevance": 86.61,
|
|
365
|
+
"arena_rating": 1455.1695813915626,
|
|
366
|
+
"arena_rank": 47,
|
|
367
|
+
"composite": 0.9166997650018204,
|
|
368
|
+
"composite_rank": 32
|
|
369
|
+
},
|
|
370
|
+
{
|
|
371
|
+
"name": "glm-5.2 (max)",
|
|
372
|
+
"norm": "glm-5.2 (max)",
|
|
373
|
+
"bfcl_overall": null,
|
|
374
|
+
"bfcl_multi_turn": null,
|
|
375
|
+
"bfcl_irrelevance": null,
|
|
376
|
+
"arena_rating": 1465.0166666115326,
|
|
377
|
+
"arena_rank": 33,
|
|
378
|
+
"composite": 0.9142091152815013,
|
|
379
|
+
"composite_rank": 33
|
|
380
|
+
},
|
|
381
|
+
{
|
|
382
|
+
"name": "qwen3.5-max-preview",
|
|
383
|
+
"norm": "qwen3.5-max-preview",
|
|
384
|
+
"bfcl_overall": null,
|
|
385
|
+
"bfcl_multi_turn": null,
|
|
386
|
+
"bfcl_irrelevance": null,
|
|
387
|
+
"arena_rating": 1464.9393207966946,
|
|
388
|
+
"arena_rank": 34,
|
|
389
|
+
"composite": 0.9115281501340482,
|
|
390
|
+
"composite_rank": 34
|
|
391
|
+
},
|
|
392
|
+
{
|
|
393
|
+
"name": "Claude-Opus-4-5-20251101 (FC)",
|
|
394
|
+
"norm": "claude-opus-4-5-20251101",
|
|
395
|
+
"bfcl_overall": 77.47,
|
|
396
|
+
"bfcl_multi_turn": 68.38,
|
|
397
|
+
"bfcl_irrelevance": 84.72,
|
|
398
|
+
"arena_rating": 1469.11292416339,
|
|
399
|
+
"arena_rank": 28,
|
|
400
|
+
"composite": 0.910915830933704,
|
|
401
|
+
"composite_rank": 35
|
|
402
|
+
},
|
|
403
|
+
{
|
|
404
|
+
"name": "grok-4.5",
|
|
405
|
+
"norm": "grok-4.5",
|
|
406
|
+
"bfcl_overall": null,
|
|
407
|
+
"bfcl_multi_turn": null,
|
|
408
|
+
"bfcl_irrelevance": null,
|
|
409
|
+
"arena_rating": 1463.9447851222333,
|
|
410
|
+
"arena_rank": 35,
|
|
411
|
+
"composite": 0.9088471849865951,
|
|
412
|
+
"composite_rank": 36
|
|
413
|
+
},
|
|
414
|
+
{
|
|
415
|
+
"name": "claude-sonnet-5-high",
|
|
416
|
+
"norm": "claude-sonnet-5-high",
|
|
417
|
+
"bfcl_overall": null,
|
|
418
|
+
"bfcl_multi_turn": null,
|
|
419
|
+
"bfcl_irrelevance": null,
|
|
420
|
+
"arena_rating": 1463.7350665800734,
|
|
421
|
+
"arena_rank": 36,
|
|
422
|
+
"composite": 0.9061662198391421,
|
|
423
|
+
"composite_rank": 37
|
|
424
|
+
},
|
|
425
|
+
{
|
|
426
|
+
"name": "Gemini-3-Pro-Preview (Prompt)",
|
|
427
|
+
"norm": "gemini-3-pro-preview",
|
|
428
|
+
"bfcl_overall": 72.51,
|
|
429
|
+
"bfcl_multi_turn": 60.75,
|
|
430
|
+
"bfcl_irrelevance": 85.59,
|
|
431
|
+
"composite": 0.9053497942386831,
|
|
432
|
+
"composite_rank": 38
|
|
433
|
+
},
|
|
434
|
+
{
|
|
435
|
+
"name": "kimi-k2.6",
|
|
436
|
+
"norm": "kimi-k2.6",
|
|
437
|
+
"bfcl_overall": null,
|
|
438
|
+
"bfcl_multi_turn": null,
|
|
439
|
+
"bfcl_irrelevance": null,
|
|
440
|
+
"arena_rating": 1461.7444934413968,
|
|
441
|
+
"arena_rank": 37,
|
|
442
|
+
"composite": 0.903485254691689,
|
|
443
|
+
"composite_rank": 39
|
|
444
|
+
},
|
|
445
|
+
{
|
|
446
|
+
"name": "qwen3.6-max-preview",
|
|
447
|
+
"norm": "qwen3.6-max-preview",
|
|
448
|
+
"bfcl_overall": null,
|
|
449
|
+
"bfcl_multi_turn": null,
|
|
450
|
+
"bfcl_irrelevance": null,
|
|
451
|
+
"arena_rating": 1460.288544125702,
|
|
452
|
+
"arena_rank": 38,
|
|
453
|
+
"composite": 0.900804289544236,
|
|
454
|
+
"composite_rank": 40
|
|
455
|
+
},
|
|
456
|
+
{
|
|
457
|
+
"name": "qwen3.7-plus",
|
|
458
|
+
"norm": "qwen3.7-plus",
|
|
459
|
+
"bfcl_overall": null,
|
|
460
|
+
"bfcl_multi_turn": null,
|
|
461
|
+
"bfcl_irrelevance": null,
|
|
462
|
+
"arena_rating": 1459.6071879722635,
|
|
463
|
+
"arena_rank": 39,
|
|
464
|
+
"composite": 0.8981233243967829,
|
|
465
|
+
"composite_rank": 41
|
|
466
|
+
},
|
|
467
|
+
{
|
|
468
|
+
"name": "grok-4.1",
|
|
469
|
+
"norm": "grok-4.1",
|
|
470
|
+
"bfcl_overall": null,
|
|
471
|
+
"bfcl_multi_turn": null,
|
|
472
|
+
"bfcl_irrelevance": null,
|
|
473
|
+
"arena_rating": 1459.5099302954277,
|
|
474
|
+
"arena_rank": 40,
|
|
475
|
+
"composite": 0.8954423592493298,
|
|
476
|
+
"composite_rank": 42
|
|
477
|
+
},
|
|
478
|
+
{
|
|
479
|
+
"name": "gemini-3-flash (thinking-minimal)",
|
|
480
|
+
"norm": "gemini-3-flash (thinking-minimal)",
|
|
481
|
+
"bfcl_overall": null,
|
|
482
|
+
"bfcl_multi_turn": null,
|
|
483
|
+
"bfcl_irrelevance": null,
|
|
484
|
+
"arena_rating": 1459.4717800250137,
|
|
485
|
+
"arena_rank": 41,
|
|
486
|
+
"composite": 0.8927613941018767,
|
|
487
|
+
"composite_rank": 43
|
|
488
|
+
},
|
|
489
|
+
{
|
|
490
|
+
"name": "deepseek-v4-pro-thinking",
|
|
491
|
+
"norm": "deepseek-v4-pro-thinking",
|
|
492
|
+
"bfcl_overall": null,
|
|
493
|
+
"bfcl_multi_turn": null,
|
|
494
|
+
"bfcl_irrelevance": null,
|
|
495
|
+
"arena_rating": 1456.7564728797358,
|
|
496
|
+
"arena_rank": 42,
|
|
497
|
+
"composite": 0.8900804289544236,
|
|
498
|
+
"composite_rank": 44
|
|
499
|
+
},
|
|
500
|
+
{
|
|
501
|
+
"name": "Moonshotai-Kimi-K2-Instruct (FC)",
|
|
502
|
+
"norm": "moonshotai-kimi-k2-instruct",
|
|
503
|
+
"bfcl_overall": 59.06,
|
|
504
|
+
"bfcl_multi_turn": 50.63,
|
|
505
|
+
"bfcl_irrelevance": 87.34,
|
|
506
|
+
"composite": 0.888888888888889,
|
|
507
|
+
"composite_rank": 45
|
|
508
|
+
},
|
|
509
|
+
{
|
|
510
|
+
"name": "deepseek-v4-pro",
|
|
511
|
+
"norm": "deepseek-v4-pro",
|
|
512
|
+
"bfcl_overall": null,
|
|
513
|
+
"bfcl_multi_turn": null,
|
|
514
|
+
"bfcl_irrelevance": null,
|
|
515
|
+
"arena_rating": 1456.7100376606486,
|
|
516
|
+
"arena_rank": 43,
|
|
517
|
+
"composite": 0.8873994638069705,
|
|
518
|
+
"composite_rank": 46
|
|
519
|
+
},
|
|
520
|
+
{
|
|
521
|
+
"name": "glm-5",
|
|
522
|
+
"norm": "glm-5",
|
|
523
|
+
"bfcl_overall": null,
|
|
524
|
+
"bfcl_multi_turn": null,
|
|
525
|
+
"bfcl_irrelevance": null,
|
|
526
|
+
"arena_rating": 1456.4564684221318,
|
|
527
|
+
"arena_rank": 44,
|
|
528
|
+
"composite": 0.8847184986595175,
|
|
529
|
+
"composite_rank": 47
|
|
530
|
+
},
|
|
531
|
+
{
|
|
532
|
+
"name": "claude-sonnet-4-5-20250929-thinking-32k",
|
|
533
|
+
"norm": "claude-sonnet-4-5-20250929-thinking-32k",
|
|
534
|
+
"bfcl_overall": null,
|
|
535
|
+
"bfcl_multi_turn": null,
|
|
536
|
+
"bfcl_irrelevance": null,
|
|
537
|
+
"arena_rating": 1455.5938647465432,
|
|
538
|
+
"arena_rank": 45,
|
|
539
|
+
"composite": 0.8820375335120644,
|
|
540
|
+
"composite_rank": 48
|
|
541
|
+
},
|
|
542
|
+
{
|
|
543
|
+
"name": "dola-seed-2.0-pro",
|
|
544
|
+
"norm": "dola-seed-2.0-pro",
|
|
545
|
+
"bfcl_overall": null,
|
|
546
|
+
"bfcl_multi_turn": null,
|
|
547
|
+
"bfcl_irrelevance": null,
|
|
548
|
+
"arena_rating": 1455.2295985289359,
|
|
549
|
+
"arena_rank": 46,
|
|
550
|
+
"composite": 0.8793565683646113,
|
|
551
|
+
"composite_rank": 49
|
|
552
|
+
},
|
|
553
|
+
{
|
|
554
|
+
"name": "gpt-5.1-high",
|
|
555
|
+
"norm": "gpt-5.1-high",
|
|
556
|
+
"bfcl_overall": null,
|
|
557
|
+
"bfcl_multi_turn": null,
|
|
558
|
+
"bfcl_irrelevance": null,
|
|
559
|
+
"arena_rating": 1454.618217190334,
|
|
560
|
+
"arena_rank": 48,
|
|
561
|
+
"composite": 0.8739946380697051,
|
|
562
|
+
"composite_rank": 50
|
|
563
|
+
},
|
|
564
|
+
{
|
|
565
|
+
"name": "gemma-4-31b",
|
|
566
|
+
"norm": "gemma-4-31b",
|
|
567
|
+
"bfcl_overall": null,
|
|
568
|
+
"bfcl_multi_turn": null,
|
|
569
|
+
"bfcl_irrelevance": null,
|
|
570
|
+
"arena_rating": 1451.0992723516772,
|
|
571
|
+
"arena_rank": 49,
|
|
572
|
+
"composite": 0.871313672922252,
|
|
573
|
+
"composite_rank": 51
|
|
574
|
+
},
|
|
575
|
+
{
|
|
576
|
+
"name": "gpt-5.4-mini-high",
|
|
577
|
+
"norm": "gpt-5.4-mini-high",
|
|
578
|
+
"bfcl_overall": null,
|
|
579
|
+
"bfcl_multi_turn": null,
|
|
580
|
+
"bfcl_irrelevance": null,
|
|
581
|
+
"arena_rating": 1449.3657239119348,
|
|
582
|
+
"arena_rank": 50,
|
|
583
|
+
"composite": 0.868632707774799,
|
|
584
|
+
"composite_rank": 52
|
|
585
|
+
},
|
|
586
|
+
{
|
|
587
|
+
"name": "kimi-k2.5-thinking",
|
|
588
|
+
"norm": "kimi-k2.5-thinking",
|
|
589
|
+
"bfcl_overall": null,
|
|
590
|
+
"bfcl_multi_turn": null,
|
|
591
|
+
"bfcl_irrelevance": null,
|
|
592
|
+
"arena_rating": 1449.2889981569624,
|
|
593
|
+
"arena_rank": 51,
|
|
594
|
+
"composite": 0.8659517426273459,
|
|
595
|
+
"composite_rank": 53
|
|
596
|
+
},
|
|
597
|
+
{
|
|
598
|
+
"name": "GPT-5-mini-2025-08-07 (FC)",
|
|
599
|
+
"norm": "gpt-5-mini-2025-08-07",
|
|
600
|
+
"bfcl_overall": 55.46,
|
|
601
|
+
"bfcl_multi_turn": 27.5,
|
|
602
|
+
"bfcl_irrelevance": 91.01,
|
|
603
|
+
"composite": 0.8641975308641975,
|
|
604
|
+
"composite_rank": 54
|
|
605
|
+
},
|
|
606
|
+
{
|
|
607
|
+
"name": "claude-opus-4-1-20250805-thinking-16k",
|
|
608
|
+
"norm": "claude-opus-4-1-20250805-thinking-16k",
|
|
609
|
+
"bfcl_overall": null,
|
|
610
|
+
"bfcl_multi_turn": null,
|
|
611
|
+
"bfcl_irrelevance": null,
|
|
612
|
+
"arena_rating": 1449.1214135051353,
|
|
613
|
+
"arena_rank": 52,
|
|
614
|
+
"composite": 0.8632707774798928,
|
|
615
|
+
"composite_rank": 55
|
|
616
|
+
},
|
|
617
|
+
{
|
|
618
|
+
"name": "gpt-5.3-chat-latest",
|
|
619
|
+
"norm": "gpt-5.3-chat-latest",
|
|
620
|
+
"bfcl_overall": null,
|
|
621
|
+
"bfcl_multi_turn": null,
|
|
622
|
+
"bfcl_irrelevance": null,
|
|
623
|
+
"arena_rating": 1448.9962857389828,
|
|
624
|
+
"arena_rank": 53,
|
|
625
|
+
"composite": 0.8605898123324397,
|
|
626
|
+
"composite_rank": 56
|
|
627
|
+
},
|
|
628
|
+
{
|
|
629
|
+
"name": "Command A Reasoning (FC)",
|
|
630
|
+
"norm": "command a reasoning",
|
|
631
|
+
"bfcl_overall": 57.06,
|
|
632
|
+
"bfcl_multi_turn": 50.12,
|
|
633
|
+
"bfcl_irrelevance": 86.75,
|
|
634
|
+
"composite": 0.8600823045267489,
|
|
635
|
+
"composite_rank": 57
|
|
636
|
+
},
|
|
637
|
+
{
|
|
638
|
+
"name": "GLM-4.6 (FC thinking)",
|
|
639
|
+
"norm": "glm-4.6",
|
|
640
|
+
"bfcl_overall": 72.38,
|
|
641
|
+
"bfcl_multi_turn": 68,
|
|
642
|
+
"bfcl_irrelevance": 84.96,
|
|
643
|
+
"arena_rating": 1425.266044744211,
|
|
644
|
+
"arena_rank": 86,
|
|
645
|
+
"composite": 0.8596961572832887,
|
|
646
|
+
"composite_rank": 58
|
|
647
|
+
},
|
|
648
|
+
{
|
|
649
|
+
"name": "ernie-5.0-preview-1203",
|
|
650
|
+
"norm": "ernie-5.0-preview-1203",
|
|
651
|
+
"bfcl_overall": null,
|
|
652
|
+
"bfcl_multi_turn": null,
|
|
653
|
+
"bfcl_irrelevance": null,
|
|
654
|
+
"arena_rating": 1448.9057677915346,
|
|
655
|
+
"arena_rank": 54,
|
|
656
|
+
"composite": 0.8579088471849866,
|
|
657
|
+
"composite_rank": 59
|
|
658
|
+
},
|
|
659
|
+
{
|
|
660
|
+
"name": "mimo-v2-pro",
|
|
661
|
+
"norm": "mimo-v2-pro",
|
|
662
|
+
"bfcl_overall": null,
|
|
663
|
+
"bfcl_multi_turn": null,
|
|
664
|
+
"bfcl_irrelevance": null,
|
|
665
|
+
"arena_rating": 1448.5358083369135,
|
|
666
|
+
"arena_rank": 55,
|
|
667
|
+
"composite": 0.8552278820375335,
|
|
668
|
+
"composite_rank": 60
|
|
669
|
+
},
|
|
670
|
+
{
|
|
671
|
+
"name": "claude-opus-4-1-20250805",
|
|
672
|
+
"norm": "claude-opus-4-1-20250805",
|
|
673
|
+
"bfcl_overall": null,
|
|
674
|
+
"bfcl_multi_turn": null,
|
|
675
|
+
"bfcl_irrelevance": null,
|
|
676
|
+
"arena_rating": 1447.089134171389,
|
|
677
|
+
"arena_rank": 56,
|
|
678
|
+
"composite": 0.8525469168900804,
|
|
679
|
+
"composite_rank": 61
|
|
680
|
+
},
|
|
681
|
+
{
|
|
682
|
+
"name": "ernie-5.0-0110",
|
|
683
|
+
"norm": "ernie-5.0-0110",
|
|
684
|
+
"bfcl_overall": null,
|
|
685
|
+
"bfcl_multi_turn": null,
|
|
686
|
+
"bfcl_irrelevance": null,
|
|
687
|
+
"arena_rating": 1447.0583124019943,
|
|
688
|
+
"arena_rank": 57,
|
|
689
|
+
"composite": 0.8498659517426274,
|
|
690
|
+
"composite_rank": 62
|
|
691
|
+
},
|
|
692
|
+
{
|
|
693
|
+
"name": "gemini-2.5-pro",
|
|
694
|
+
"norm": "gemini-2.5-pro",
|
|
695
|
+
"bfcl_overall": null,
|
|
696
|
+
"bfcl_multi_turn": null,
|
|
697
|
+
"bfcl_irrelevance": null,
|
|
698
|
+
"arena_rating": 1445.69371437698,
|
|
699
|
+
"arena_rank": 58,
|
|
700
|
+
"composite": 0.8471849865951743,
|
|
701
|
+
"composite_rank": 63
|
|
702
|
+
},
|
|
703
|
+
{
|
|
704
|
+
"name": "minimax-m3",
|
|
705
|
+
"norm": "minimax-m3",
|
|
706
|
+
"bfcl_overall": null,
|
|
707
|
+
"bfcl_multi_turn": null,
|
|
708
|
+
"bfcl_irrelevance": null,
|
|
709
|
+
"arena_rating": 1445.1239272752707,
|
|
710
|
+
"arena_rank": 59,
|
|
711
|
+
"composite": 0.8445040214477212,
|
|
712
|
+
"composite_rank": 64
|
|
713
|
+
},
|
|
714
|
+
{
|
|
715
|
+
"name": "gpt-4.5-preview-2025-02-27",
|
|
716
|
+
"norm": "gpt-4.5-preview-2025-02-27",
|
|
717
|
+
"bfcl_overall": null,
|
|
718
|
+
"bfcl_multi_turn": null,
|
|
719
|
+
"bfcl_irrelevance": null,
|
|
720
|
+
"arena_rating": 1444.6821242057295,
|
|
721
|
+
"arena_rank": 60,
|
|
722
|
+
"composite": 0.8418230563002681,
|
|
723
|
+
"composite_rank": 65
|
|
724
|
+
},
|
|
725
|
+
{
|
|
726
|
+
"name": "Gemini-2.5-Flash (FC)",
|
|
727
|
+
"norm": "gemini-2.5-flash",
|
|
728
|
+
"bfcl_overall": 56.24,
|
|
729
|
+
"bfcl_multi_turn": 36.25,
|
|
730
|
+
"bfcl_irrelevance": 93.67,
|
|
731
|
+
"arena_rating": 1410.3094370969366,
|
|
732
|
+
"arena_rank": 115,
|
|
733
|
+
"composite": 0.8402591599642539,
|
|
734
|
+
"composite_rank": 66
|
|
735
|
+
},
|
|
736
|
+
{
|
|
737
|
+
"name": "qwen3.6-plus",
|
|
738
|
+
"norm": "qwen3.6-plus",
|
|
739
|
+
"bfcl_overall": null,
|
|
740
|
+
"bfcl_multi_turn": null,
|
|
741
|
+
"bfcl_irrelevance": null,
|
|
742
|
+
"arena_rating": 1443.2838433547502,
|
|
743
|
+
"arena_rank": 61,
|
|
744
|
+
"composite": 0.839142091152815,
|
|
745
|
+
"composite_rank": 67
|
|
746
|
+
},
|
|
747
|
+
{
|
|
748
|
+
"name": "chatgpt-4o-latest-20250326",
|
|
749
|
+
"norm": "chatgpt-4o-latest-20250326",
|
|
750
|
+
"bfcl_overall": null,
|
|
751
|
+
"bfcl_multi_turn": null,
|
|
752
|
+
"bfcl_irrelevance": null,
|
|
753
|
+
"arena_rating": 1443.1869061396271,
|
|
754
|
+
"arena_rank": 62,
|
|
755
|
+
"composite": 0.8364611260053619,
|
|
756
|
+
"composite_rank": 68
|
|
757
|
+
},
|
|
758
|
+
{
|
|
759
|
+
"name": "grok-4.3",
|
|
760
|
+
"norm": "grok-4.3",
|
|
761
|
+
"bfcl_overall": null,
|
|
762
|
+
"bfcl_multi_turn": null,
|
|
763
|
+
"bfcl_irrelevance": null,
|
|
764
|
+
"arena_rating": 1442.667087617281,
|
|
765
|
+
"arena_rank": 63,
|
|
766
|
+
"composite": 0.8337801608579088,
|
|
767
|
+
"composite_rank": 69
|
|
768
|
+
},
|
|
769
|
+
{
|
|
770
|
+
"name": "Claude-Haiku-4-5-20251001 (FC)",
|
|
771
|
+
"norm": "claude-haiku-4-5-20251001",
|
|
772
|
+
"bfcl_overall": 68.7,
|
|
773
|
+
"bfcl_multi_turn": 53.62,
|
|
774
|
+
"bfcl_irrelevance": 85.11,
|
|
775
|
+
"arena_rating": 1412.1187623275694,
|
|
776
|
+
"arena_rank": 112,
|
|
777
|
+
"composite": 0.8330106245655844,
|
|
778
|
+
"composite_rank": 70
|
|
779
|
+
},
|
|
780
|
+
{
|
|
781
|
+
"name": "glm-4.7",
|
|
782
|
+
"norm": "glm-4.7",
|
|
783
|
+
"bfcl_overall": null,
|
|
784
|
+
"bfcl_multi_turn": null,
|
|
785
|
+
"bfcl_irrelevance": null,
|
|
786
|
+
"arena_rating": 1442.4030933560018,
|
|
787
|
+
"arena_rank": 64,
|
|
788
|
+
"composite": 0.8310991957104558,
|
|
789
|
+
"composite_rank": 71
|
|
790
|
+
},
|
|
791
|
+
{
|
|
792
|
+
"name": "o3-2025-04-16 (Prompt)",
|
|
793
|
+
"norm": "o3-2025-04-16",
|
|
794
|
+
"bfcl_overall": 63.05,
|
|
795
|
+
"bfcl_multi_turn": 62.25,
|
|
796
|
+
"bfcl_irrelevance": 83.98,
|
|
797
|
+
"arena_rating": 1430.9432622268507,
|
|
798
|
+
"arena_rank": 80,
|
|
799
|
+
"composite": 0.8297669877205177,
|
|
800
|
+
"composite_rank": 72
|
|
801
|
+
},
|
|
802
|
+
{
|
|
803
|
+
"name": "qwen3.5-397b-a17b",
|
|
804
|
+
"norm": "qwen3.5-397b-a17b",
|
|
805
|
+
"bfcl_overall": null,
|
|
806
|
+
"bfcl_multi_turn": null,
|
|
807
|
+
"bfcl_irrelevance": null,
|
|
808
|
+
"arena_rating": 1441.6971376085967,
|
|
809
|
+
"arena_rank": 65,
|
|
810
|
+
"composite": 0.8284182305630027,
|
|
811
|
+
"composite_rank": 73
|
|
812
|
+
},
|
|
813
|
+
{
|
|
814
|
+
"name": "gpt-5.1",
|
|
815
|
+
"norm": "gpt-5.1",
|
|
816
|
+
"bfcl_overall": null,
|
|
817
|
+
"bfcl_multi_turn": null,
|
|
818
|
+
"bfcl_irrelevance": null,
|
|
819
|
+
"arena_rating": 1438.6937894442424,
|
|
820
|
+
"arena_rank": 66,
|
|
821
|
+
"composite": 0.8257372654155496,
|
|
822
|
+
"composite_rank": 74
|
|
823
|
+
},
|
|
824
|
+
{
|
|
825
|
+
"name": "deepseek-v4-flash-thinking",
|
|
826
|
+
"norm": "deepseek-v4-flash-thinking",
|
|
827
|
+
"bfcl_overall": null,
|
|
828
|
+
"bfcl_multi_turn": null,
|
|
829
|
+
"bfcl_irrelevance": null,
|
|
830
|
+
"arena_rating": 1438.1564770998718,
|
|
831
|
+
"arena_rank": 67,
|
|
832
|
+
"composite": 0.8230563002680965,
|
|
833
|
+
"composite_rank": 75
|
|
834
|
+
},
|
|
835
|
+
{
|
|
836
|
+
"name": "glm-5v-turbo",
|
|
837
|
+
"norm": "glm-5v-turbo",
|
|
838
|
+
"bfcl_overall": null,
|
|
839
|
+
"bfcl_multi_turn": null,
|
|
840
|
+
"bfcl_irrelevance": null,
|
|
841
|
+
"arena_rating": 1438.0977098434414,
|
|
842
|
+
"arena_rank": 68,
|
|
843
|
+
"composite": 0.8203753351206434,
|
|
844
|
+
"composite_rank": 76
|
|
845
|
+
},
|
|
846
|
+
{
|
|
847
|
+
"name": "gemma-4-26b-a4b",
|
|
848
|
+
"norm": "gemma-4-26b-a4b",
|
|
849
|
+
"bfcl_overall": null,
|
|
850
|
+
"bfcl_multi_turn": null,
|
|
851
|
+
"bfcl_irrelevance": null,
|
|
852
|
+
"arena_rating": 1438.0451294793265,
|
|
853
|
+
"arena_rank": 69,
|
|
854
|
+
"composite": 0.8176943699731903,
|
|
855
|
+
"composite_rank": 77
|
|
856
|
+
},
|
|
857
|
+
{
|
|
858
|
+
"name": "deepseek-v4-flash",
|
|
859
|
+
"norm": "deepseek-v4-flash",
|
|
860
|
+
"bfcl_overall": null,
|
|
861
|
+
"bfcl_multi_turn": null,
|
|
862
|
+
"bfcl_irrelevance": null,
|
|
863
|
+
"arena_rating": 1437.578738381932,
|
|
864
|
+
"arena_rank": 70,
|
|
865
|
+
"composite": 0.8150134048257373,
|
|
866
|
+
"composite_rank": 78
|
|
867
|
+
},
|
|
868
|
+
{
|
|
869
|
+
"name": "gpt-5.2-high",
|
|
870
|
+
"norm": "gpt-5.2-high",
|
|
871
|
+
"bfcl_overall": null,
|
|
872
|
+
"bfcl_multi_turn": null,
|
|
873
|
+
"bfcl_irrelevance": null,
|
|
874
|
+
"arena_rating": 1437.3615124819225,
|
|
875
|
+
"arena_rank": 71,
|
|
876
|
+
"composite": 0.8123324396782842,
|
|
877
|
+
"composite_rank": 79
|
|
878
|
+
},
|
|
879
|
+
{
|
|
880
|
+
"name": "longcat-flash-chat-2602-exp",
|
|
881
|
+
"norm": "longcat-flash-chat-2602-exp",
|
|
882
|
+
"bfcl_overall": null,
|
|
883
|
+
"bfcl_multi_turn": null,
|
|
884
|
+
"bfcl_irrelevance": null,
|
|
885
|
+
"arena_rating": 1435.7547134796346,
|
|
886
|
+
"arena_rank": 72,
|
|
887
|
+
"composite": 0.8096514745308311,
|
|
888
|
+
"composite_rank": 80
|
|
889
|
+
},
|
|
890
|
+
{
|
|
891
|
+
"name": "gpt-5.2",
|
|
892
|
+
"norm": "gpt-5.2",
|
|
893
|
+
"bfcl_overall": null,
|
|
894
|
+
"bfcl_multi_turn": null,
|
|
895
|
+
"bfcl_irrelevance": null,
|
|
896
|
+
"arena_rating": 1435.3583988365826,
|
|
897
|
+
"arena_rank": 73,
|
|
898
|
+
"composite": 0.806970509383378,
|
|
899
|
+
"composite_rank": 81
|
|
900
|
+
},
|
|
901
|
+
{
|
|
902
|
+
"name": "Grok-4-0709 (Prompt)",
|
|
903
|
+
"norm": "grok-4-0709",
|
|
904
|
+
"bfcl_overall": 62.97,
|
|
905
|
+
"bfcl_multi_turn": 47,
|
|
906
|
+
"bfcl_irrelevance": 84.3,
|
|
907
|
+
"arena_rating": 1409.7350489657608,
|
|
908
|
+
"arena_rank": 116,
|
|
909
|
+
"composite": 0.80563830139344,
|
|
910
|
+
"composite_rank": 82
|
|
911
|
+
},
|
|
912
|
+
{
|
|
913
|
+
"name": "qwen3-max-preview",
|
|
914
|
+
"norm": "qwen3-max-preview",
|
|
915
|
+
"bfcl_overall": null,
|
|
916
|
+
"bfcl_multi_turn": null,
|
|
917
|
+
"bfcl_irrelevance": null,
|
|
918
|
+
"arena_rating": 1434.8171072350308,
|
|
919
|
+
"arena_rank": 74,
|
|
920
|
+
"composite": 0.8042895442359249,
|
|
921
|
+
"composite_rank": 83
|
|
922
|
+
},
|
|
923
|
+
{
|
|
924
|
+
"name": "GPT-5-nano-2025-08-07 (FC)",
|
|
925
|
+
"norm": "gpt-5-nano-2025-08-07",
|
|
926
|
+
"bfcl_overall": 51.45,
|
|
927
|
+
"bfcl_multi_turn": 34.5,
|
|
928
|
+
"bfcl_irrelevance": 89.1,
|
|
929
|
+
"composite": 0.8024691358024691,
|
|
930
|
+
"composite_rank": 84
|
|
931
|
+
},
|
|
932
|
+
{
|
|
933
|
+
"name": "gpt-5-high",
|
|
934
|
+
"norm": "gpt-5-high",
|
|
935
|
+
"bfcl_overall": null,
|
|
936
|
+
"bfcl_multi_turn": null,
|
|
937
|
+
"bfcl_irrelevance": null,
|
|
938
|
+
"arena_rating": 1433.7987859035668,
|
|
939
|
+
"arena_rank": 75,
|
|
940
|
+
"composite": 0.8016085790884718,
|
|
941
|
+
"composite_rank": 85
|
|
942
|
+
},
|
|
943
|
+
{
|
|
944
|
+
"name": "mimo-v2.5",
|
|
945
|
+
"norm": "mimo-v2.5",
|
|
946
|
+
"bfcl_overall": null,
|
|
947
|
+
"bfcl_multi_turn": null,
|
|
948
|
+
"bfcl_irrelevance": null,
|
|
949
|
+
"arena_rating": 1433.2140594922648,
|
|
950
|
+
"arena_rank": 76,
|
|
951
|
+
"composite": 0.7989276139410187,
|
|
952
|
+
"composite_rank": 86
|
|
953
|
+
},
|
|
954
|
+
{
|
|
955
|
+
"name": "gemini-3.1-flash-lite-preview",
|
|
956
|
+
"norm": "gemini-3.1-flash-lite-preview",
|
|
957
|
+
"bfcl_overall": null,
|
|
958
|
+
"bfcl_multi_turn": null,
|
|
959
|
+
"bfcl_irrelevance": null,
|
|
960
|
+
"arena_rating": 1431.5998806235973,
|
|
961
|
+
"arena_rank": 77,
|
|
962
|
+
"composite": 0.7962466487935657,
|
|
963
|
+
"composite_rank": 87
|
|
964
|
+
},
|
|
965
|
+
{
|
|
966
|
+
"name": "kimi-k2.5-instant",
|
|
967
|
+
"norm": "kimi-k2.5-instant",
|
|
968
|
+
"bfcl_overall": null,
|
|
969
|
+
"bfcl_multi_turn": null,
|
|
970
|
+
"bfcl_irrelevance": null,
|
|
971
|
+
"arena_rating": 1431.516713283509,
|
|
972
|
+
"arena_rank": 78,
|
|
973
|
+
"composite": 0.7935656836461126,
|
|
974
|
+
"composite_rank": 88
|
|
975
|
+
},
|
|
976
|
+
{
|
|
977
|
+
"name": "Grok-4-1-fast-reasoning (FC)",
|
|
978
|
+
"norm": "grok-4-1-fast-reasoning",
|
|
979
|
+
"bfcl_overall": 69.57,
|
|
980
|
+
"bfcl_multi_turn": 58.87,
|
|
981
|
+
"bfcl_irrelevance": 79.43,
|
|
982
|
+
"arena_rating": 1430.9738300666027,
|
|
983
|
+
"arena_rank": 79,
|
|
984
|
+
"composite": 0.7934001919703438,
|
|
985
|
+
"composite_rank": 89
|
|
986
|
+
},
|
|
987
|
+
{
|
|
988
|
+
"name": "mimo-v2-omni",
|
|
989
|
+
"norm": "mimo-v2-omni",
|
|
990
|
+
"bfcl_overall": null,
|
|
991
|
+
"bfcl_multi_turn": null,
|
|
992
|
+
"bfcl_irrelevance": null,
|
|
993
|
+
"arena_rating": 1430.0721929194024,
|
|
994
|
+
"arena_rank": 81,
|
|
995
|
+
"composite": 0.7855227882037533,
|
|
996
|
+
"composite_rank": 90
|
|
997
|
+
},
|
|
998
|
+
{
|
|
999
|
+
"name": "kimi-k2-thinking-turbo",
|
|
1000
|
+
"norm": "kimi-k2-thinking-turbo",
|
|
1001
|
+
"bfcl_overall": null,
|
|
1002
|
+
"bfcl_multi_turn": null,
|
|
1003
|
+
"bfcl_irrelevance": null,
|
|
1004
|
+
"arena_rating": 1429.8000993758644,
|
|
1005
|
+
"arena_rank": 82,
|
|
1006
|
+
"composite": 0.7828418230563002,
|
|
1007
|
+
"composite_rank": 91
|
|
1008
|
+
},
|
|
1009
|
+
{
|
|
1010
|
+
"name": "mistral-medium-3.5",
|
|
1011
|
+
"norm": "mistral-medium-3.5",
|
|
1012
|
+
"bfcl_overall": null,
|
|
1013
|
+
"bfcl_multi_turn": null,
|
|
1014
|
+
"bfcl_irrelevance": null,
|
|
1015
|
+
"arena_rating": 1427.1705734402979,
|
|
1016
|
+
"arena_rank": 83,
|
|
1017
|
+
"composite": 0.7801608579088471,
|
|
1018
|
+
"composite_rank": 92
|
|
1019
|
+
},
|
|
1020
|
+
{
|
|
1021
|
+
"name": "GPT-4.1-2025-04-14 (FC)",
|
|
1022
|
+
"norm": "gpt-4.1-2025-04-14",
|
|
1023
|
+
"bfcl_overall": 53.96,
|
|
1024
|
+
"bfcl_multi_turn": 38.88,
|
|
1025
|
+
"bfcl_irrelevance": 86.52,
|
|
1026
|
+
"arena_rating": 1413.7294748931563,
|
|
1027
|
+
"arena_rank": 109,
|
|
1028
|
+
"composite": 0.7794657928706186,
|
|
1029
|
+
"composite_rank": 93
|
|
1030
|
+
},
|
|
1031
|
+
{
|
|
1032
|
+
"name": "amazon-nova-experimental-chat-26-02-10",
|
|
1033
|
+
"norm": "amazon-nova-experimental-chat-26-02-10",
|
|
1034
|
+
"bfcl_overall": null,
|
|
1035
|
+
"bfcl_multi_turn": null,
|
|
1036
|
+
"bfcl_irrelevance": null,
|
|
1037
|
+
"arena_rating": 1426.877741751016,
|
|
1038
|
+
"arena_rank": 84,
|
|
1039
|
+
"composite": 0.7774798927613941,
|
|
1040
|
+
"composite_rank": 94
|
|
1041
|
+
},
|
|
1042
|
+
{
|
|
1043
|
+
"name": "gpt-5-chat",
|
|
1044
|
+
"norm": "gpt-5-chat",
|
|
1045
|
+
"bfcl_overall": null,
|
|
1046
|
+
"bfcl_multi_turn": null,
|
|
1047
|
+
"bfcl_irrelevance": null,
|
|
1048
|
+
"arena_rating": 1426.7530455355989,
|
|
1049
|
+
"arena_rank": 85,
|
|
1050
|
+
"composite": 0.774798927613941,
|
|
1051
|
+
"composite_rank": 95
|
|
1052
|
+
},
|
|
1053
|
+
{
|
|
1054
|
+
"name": "BitAgent-Bounty-8B",
|
|
1055
|
+
"norm": "bitagent-bounty-8b",
|
|
1056
|
+
"bfcl_overall": 46.23,
|
|
1057
|
+
"bfcl_multi_turn": 62.38,
|
|
1058
|
+
"bfcl_irrelevance": 97.48,
|
|
1059
|
+
"composite": 0.7695473251028807,
|
|
1060
|
+
"composite_rank": 96
|
|
1061
|
+
},
|
|
1062
|
+
{
|
|
1063
|
+
"name": "deepseek-v3.2",
|
|
1064
|
+
"norm": "deepseek-v3.2",
|
|
1065
|
+
"bfcl_overall": null,
|
|
1066
|
+
"bfcl_multi_turn": null,
|
|
1067
|
+
"bfcl_irrelevance": null,
|
|
1068
|
+
"arena_rating": 1425.098737882064,
|
|
1069
|
+
"arena_rank": 87,
|
|
1070
|
+
"composite": 0.7694369973190349,
|
|
1071
|
+
"composite_rank": 97
|
|
1072
|
+
},
|
|
1073
|
+
{
|
|
1074
|
+
"name": "deepseek-v3.2-exp-thinking",
|
|
1075
|
+
"norm": "deepseek-v3.2-exp-thinking",
|
|
1076
|
+
"bfcl_overall": null,
|
|
1077
|
+
"bfcl_multi_turn": null,
|
|
1078
|
+
"bfcl_irrelevance": null,
|
|
1079
|
+
"arena_rating": 1424.8283772715001,
|
|
1080
|
+
"arena_rank": 88,
|
|
1081
|
+
"composite": 0.7667560321715818,
|
|
1082
|
+
"composite_rank": 98
|
|
1083
|
+
},
|
|
1084
|
+
{
|
|
1085
|
+
"name": "claude-opus-4-20250514-thinking-16k",
|
|
1086
|
+
"norm": "claude-opus-4-20250514-thinking-16k",
|
|
1087
|
+
"bfcl_overall": null,
|
|
1088
|
+
"bfcl_multi_turn": null,
|
|
1089
|
+
"bfcl_irrelevance": null,
|
|
1090
|
+
"arena_rating": 1424.478218225065,
|
|
1091
|
+
"arena_rank": 89,
|
|
1092
|
+
"composite": 0.7640750670241288,
|
|
1093
|
+
"composite_rank": 99
|
|
1094
|
+
},
|
|
1095
|
+
{
|
|
1096
|
+
"name": "qwen3-max-2025-09-23",
|
|
1097
|
+
"norm": "qwen3-max-2025-09-23",
|
|
1098
|
+
"bfcl_overall": null,
|
|
1099
|
+
"bfcl_multi_turn": null,
|
|
1100
|
+
"bfcl_irrelevance": null,
|
|
1101
|
+
"arena_rating": 1424.2587912467898,
|
|
1102
|
+
"arena_rank": 90,
|
|
1103
|
+
"composite": 0.7613941018766757,
|
|
1104
|
+
"composite_rank": 100
|
|
1105
|
+
},
|
|
1106
|
+
{
|
|
1107
|
+
"name": "deepseek-v3.2-thinking",
|
|
1108
|
+
"norm": "deepseek-v3.2-thinking",
|
|
1109
|
+
"bfcl_overall": null,
|
|
1110
|
+
"bfcl_multi_turn": null,
|
|
1111
|
+
"bfcl_irrelevance": null,
|
|
1112
|
+
"arena_rating": 1423.0729163681242,
|
|
1113
|
+
"arena_rank": 92,
|
|
1114
|
+
"composite": 0.7560321715817695,
|
|
1115
|
+
"composite_rank": 101
|
|
1116
|
+
},
|
|
1117
|
+
{
|
|
1118
|
+
"name": "nvidia-nemotron-3-ultra-550b-a55b-nvfp4",
|
|
1119
|
+
"norm": "nvidia-nemotron-3-ultra-550b-a55b-nvfp4",
|
|
1120
|
+
"bfcl_overall": null,
|
|
1121
|
+
"bfcl_multi_turn": null,
|
|
1122
|
+
"bfcl_irrelevance": null,
|
|
1123
|
+
"arena_rating": 1422.7774743582688,
|
|
1124
|
+
"arena_rank": 94,
|
|
1125
|
+
"composite": 0.7506702412868633,
|
|
1126
|
+
"composite_rank": 102
|
|
1127
|
+
},
|
|
1128
|
+
{
|
|
1129
|
+
"name": "deepseek-r1-0528",
|
|
1130
|
+
"norm": "deepseek-r1-0528",
|
|
1131
|
+
"bfcl_overall": null,
|
|
1132
|
+
"bfcl_multi_turn": null,
|
|
1133
|
+
"bfcl_irrelevance": null,
|
|
1134
|
+
"arena_rating": 1422.1384143924495,
|
|
1135
|
+
"arena_rank": 95,
|
|
1136
|
+
"composite": 0.7479892761394102,
|
|
1137
|
+
"composite_rank": 103
|
|
1138
|
+
},
|
|
1139
|
+
{
|
|
1140
|
+
"name": "grok-4-fast-chat",
|
|
1141
|
+
"norm": "grok-4-fast-chat",
|
|
1142
|
+
"bfcl_overall": null,
|
|
1143
|
+
"bfcl_multi_turn": null,
|
|
1144
|
+
"bfcl_irrelevance": null,
|
|
1145
|
+
"arena_rating": 1420.771897976865,
|
|
1146
|
+
"arena_rank": 96,
|
|
1147
|
+
"composite": 0.7453083109919572,
|
|
1148
|
+
"composite_rank": 104
|
|
1149
|
+
},
|
|
1150
|
+
{
|
|
1151
|
+
"name": "ernie-5.0-preview-1022",
|
|
1152
|
+
"norm": "ernie-5.0-preview-1022",
|
|
1153
|
+
"bfcl_overall": null,
|
|
1154
|
+
"bfcl_multi_turn": null,
|
|
1155
|
+
"bfcl_irrelevance": null,
|
|
1156
|
+
"arena_rating": 1418.6976495306287,
|
|
1157
|
+
"arena_rank": 97,
|
|
1158
|
+
"composite": 0.7426273458445041,
|
|
1159
|
+
"composite_rank": 105
|
|
1160
|
+
},
|
|
1161
|
+
{
|
|
1162
|
+
"name": "kimi-k2-0905-preview",
|
|
1163
|
+
"norm": "kimi-k2-0905-preview",
|
|
1164
|
+
"bfcl_overall": null,
|
|
1165
|
+
"bfcl_multi_turn": null,
|
|
1166
|
+
"bfcl_irrelevance": null,
|
|
1167
|
+
"arena_rating": 1417.9959539404724,
|
|
1168
|
+
"arena_rank": 98,
|
|
1169
|
+
"composite": 0.739946380697051,
|
|
1170
|
+
"composite_rank": 106
|
|
1171
|
+
},
|
|
1172
|
+
{
|
|
1173
|
+
"name": "deepseek-v3.1-terminus-thinking",
|
|
1174
|
+
"norm": "deepseek-v3.1-terminus-thinking",
|
|
1175
|
+
"bfcl_overall": null,
|
|
1176
|
+
"bfcl_multi_turn": null,
|
|
1177
|
+
"bfcl_irrelevance": null,
|
|
1178
|
+
"arena_rating": 1417.797659472756,
|
|
1179
|
+
"arena_rank": 99,
|
|
1180
|
+
"composite": 0.7372654155495979,
|
|
1181
|
+
"composite_rank": 107
|
|
1182
|
+
},
|
|
1183
|
+
{
|
|
1184
|
+
"name": "deepseek-v3.1",
|
|
1185
|
+
"norm": "deepseek-v3.1",
|
|
1186
|
+
"bfcl_overall": null,
|
|
1187
|
+
"bfcl_multi_turn": null,
|
|
1188
|
+
"bfcl_irrelevance": null,
|
|
1189
|
+
"arena_rating": 1417.617957308197,
|
|
1190
|
+
"arena_rank": 100,
|
|
1191
|
+
"composite": 0.7345844504021448,
|
|
1192
|
+
"composite_rank": 108
|
|
1193
|
+
},
|
|
1194
|
+
{
|
|
1195
|
+
"name": "kimi-k2-0711-preview",
|
|
1196
|
+
"norm": "kimi-k2-0711-preview",
|
|
1197
|
+
"bfcl_overall": null,
|
|
1198
|
+
"bfcl_multi_turn": null,
|
|
1199
|
+
"bfcl_irrelevance": null,
|
|
1200
|
+
"arena_rating": 1417.4559804703727,
|
|
1201
|
+
"arena_rank": 101,
|
|
1202
|
+
"composite": 0.7319034852546917,
|
|
1203
|
+
"composite_rank": 109
|
|
1204
|
+
},
|
|
1205
|
+
{
|
|
1206
|
+
"name": "qwen3.5-122b-a10b",
|
|
1207
|
+
"norm": "qwen3.5-122b-a10b",
|
|
1208
|
+
"bfcl_overall": null,
|
|
1209
|
+
"bfcl_multi_turn": null,
|
|
1210
|
+
"bfcl_irrelevance": null,
|
|
1211
|
+
"arena_rating": 1417.1308793274836,
|
|
1212
|
+
"arena_rank": 102,
|
|
1213
|
+
"composite": 0.7292225201072386,
|
|
1214
|
+
"composite_rank": 110
|
|
1215
|
+
},
|
|
1216
|
+
{
|
|
1217
|
+
"name": "ToolACE-2-8B (FC)",
|
|
1218
|
+
"norm": "toolace-2-8b",
|
|
1219
|
+
"bfcl_overall": 42.44,
|
|
1220
|
+
"bfcl_multi_turn": 38.38,
|
|
1221
|
+
"bfcl_irrelevance": 90.79,
|
|
1222
|
+
"composite": 0.7283950617283951,
|
|
1223
|
+
"composite_rank": 111
|
|
1224
|
+
},
|
|
1225
|
+
{
|
|
1226
|
+
"name": "deepseek-v3.1-thinking",
|
|
1227
|
+
"norm": "deepseek-v3.1-thinking",
|
|
1228
|
+
"bfcl_overall": null,
|
|
1229
|
+
"bfcl_multi_turn": null,
|
|
1230
|
+
"bfcl_irrelevance": null,
|
|
1231
|
+
"arena_rating": 1417.0546476119,
|
|
1232
|
+
"arena_rank": 103,
|
|
1233
|
+
"composite": 0.7265415549597856,
|
|
1234
|
+
"composite_rank": 112
|
|
1235
|
+
},
|
|
1236
|
+
{
|
|
1237
|
+
"name": "minimax-m2.7",
|
|
1238
|
+
"norm": "minimax-m2.7",
|
|
1239
|
+
"bfcl_overall": null,
|
|
1240
|
+
"bfcl_multi_turn": null,
|
|
1241
|
+
"bfcl_irrelevance": null,
|
|
1242
|
+
"arena_rating": 1416.5668337583277,
|
|
1243
|
+
"arena_rank": 104,
|
|
1244
|
+
"composite": 0.7238605898123325,
|
|
1245
|
+
"composite_rank": 113
|
|
1246
|
+
},
|
|
1247
|
+
{
|
|
1248
|
+
"name": "mistral-large-3",
|
|
1249
|
+
"norm": "mistral-large-3",
|
|
1250
|
+
"bfcl_overall": null,
|
|
1251
|
+
"bfcl_multi_turn": null,
|
|
1252
|
+
"bfcl_irrelevance": null,
|
|
1253
|
+
"arena_rating": 1416.2439272212393,
|
|
1254
|
+
"arena_rank": 105,
|
|
1255
|
+
"composite": 0.7211796246648794,
|
|
1256
|
+
"composite_rank": 114
|
|
1257
|
+
},
|
|
1258
|
+
{
|
|
1259
|
+
"name": "o4-mini-2025-04-16 (FC)",
|
|
1260
|
+
"norm": "o4-mini-2025-04-16",
|
|
1261
|
+
"bfcl_overall": 53.24,
|
|
1262
|
+
"bfcl_multi_turn": 41.75,
|
|
1263
|
+
"bfcl_irrelevance": 83.91,
|
|
1264
|
+
"arena_rating": 1389.8663255713752,
|
|
1265
|
+
"arena_rank": 139,
|
|
1266
|
+
"composite": 0.7192350974745971,
|
|
1267
|
+
"composite_rank": 115
|
|
1268
|
+
},
|
|
1269
|
+
{
|
|
1270
|
+
"name": "deepseek-v3.1-terminus",
|
|
1271
|
+
"norm": "deepseek-v3.1-terminus",
|
|
1272
|
+
"bfcl_overall": null,
|
|
1273
|
+
"bfcl_multi_turn": null,
|
|
1274
|
+
"bfcl_irrelevance": null,
|
|
1275
|
+
"arena_rating": 1415.448445239601,
|
|
1276
|
+
"arena_rank": 106,
|
|
1277
|
+
"composite": 0.7184986595174263,
|
|
1278
|
+
"composite_rank": 116
|
|
1279
|
+
},
|
|
1280
|
+
{
|
|
1281
|
+
"name": "xLAM-2-32b-fc-r (FC)",
|
|
1282
|
+
"norm": "xlam-2-32b-fc-r",
|
|
1283
|
+
"bfcl_overall": 54.66,
|
|
1284
|
+
"bfcl_multi_turn": 69.5,
|
|
1285
|
+
"bfcl_irrelevance": 80.23,
|
|
1286
|
+
"composite": 0.7160493827160495,
|
|
1287
|
+
"composite_rank": 117
|
|
1288
|
+
},
|
|
1289
|
+
{
|
|
1290
|
+
"name": "GPT-5.2-2025-12-11 (FC)",
|
|
1291
|
+
"norm": "gpt-5.2-2025-12-11",
|
|
1292
|
+
"bfcl_overall": 55.87,
|
|
1293
|
+
"bfcl_multi_turn": 28.12,
|
|
1294
|
+
"bfcl_irrelevance": 79.42,
|
|
1295
|
+
"composite": 0.7160493827160493,
|
|
1296
|
+
"composite_rank": 118
|
|
1297
|
+
},
|
|
1298
|
+
{
|
|
1299
|
+
"name": "amazon-nova-experimental-chat-26-01-10",
|
|
1300
|
+
"norm": "amazon-nova-experimental-chat-26-01-10",
|
|
1301
|
+
"bfcl_overall": null,
|
|
1302
|
+
"bfcl_multi_turn": null,
|
|
1303
|
+
"bfcl_irrelevance": null,
|
|
1304
|
+
"arena_rating": 1415.4476554773298,
|
|
1305
|
+
"arena_rank": 107,
|
|
1306
|
+
"composite": 0.7158176943699732,
|
|
1307
|
+
"composite_rank": 119
|
|
1308
|
+
},
|
|
1309
|
+
{
|
|
1310
|
+
"name": "qwen3-vl-235b-a22b-instruct",
|
|
1311
|
+
"norm": "qwen3-vl-235b-a22b-instruct",
|
|
1312
|
+
"bfcl_overall": null,
|
|
1313
|
+
"bfcl_multi_turn": null,
|
|
1314
|
+
"bfcl_irrelevance": null,
|
|
1315
|
+
"arena_rating": 1415.2921963825481,
|
|
1316
|
+
"arena_rank": 108,
|
|
1317
|
+
"composite": 0.7131367292225201,
|
|
1318
|
+
"composite_rank": 120
|
|
1319
|
+
},
|
|
1320
|
+
{
|
|
1321
|
+
"name": "Nanbeige4-3B-Thinking-2511 (FC)",
|
|
1322
|
+
"norm": "nanbeige4-3b-thinking-2511",
|
|
1323
|
+
"bfcl_overall": 51.4,
|
|
1324
|
+
"bfcl_multi_turn": 51.12,
|
|
1325
|
+
"bfcl_irrelevance": 83.09,
|
|
1326
|
+
"composite": 0.7119341563786007,
|
|
1327
|
+
"composite_rank": 121
|
|
1328
|
+
},
|
|
1329
|
+
{
|
|
1330
|
+
"name": "hunyuan-hy3-preview",
|
|
1331
|
+
"norm": "hunyuan-hy3-preview",
|
|
1332
|
+
"bfcl_overall": null,
|
|
1333
|
+
"bfcl_multi_turn": null,
|
|
1334
|
+
"bfcl_irrelevance": null,
|
|
1335
|
+
"arena_rating": 1412.6676203608956,
|
|
1336
|
+
"arena_rank": 110,
|
|
1337
|
+
"composite": 0.707774798927614,
|
|
1338
|
+
"composite_rank": 122
|
|
1339
|
+
},
|
|
1340
|
+
{
|
|
1341
|
+
"name": "claude-opus-4-20250514",
|
|
1342
|
+
"norm": "claude-opus-4-20250514",
|
|
1343
|
+
"bfcl_overall": null,
|
|
1344
|
+
"bfcl_multi_turn": null,
|
|
1345
|
+
"bfcl_irrelevance": null,
|
|
1346
|
+
"arena_rating": 1412.4448929429811,
|
|
1347
|
+
"arena_rank": 111,
|
|
1348
|
+
"composite": 0.7050938337801609,
|
|
1349
|
+
"composite_rank": 123
|
|
1350
|
+
},
|
|
1351
|
+
{
|
|
1352
|
+
"name": "grok-3-preview-02-24",
|
|
1353
|
+
"norm": "grok-3-preview-02-24",
|
|
1354
|
+
"bfcl_overall": null,
|
|
1355
|
+
"bfcl_multi_turn": null,
|
|
1356
|
+
"bfcl_irrelevance": null,
|
|
1357
|
+
"arena_rating": 1411.528870684904,
|
|
1358
|
+
"arena_rank": 113,
|
|
1359
|
+
"composite": 0.6997319034852547,
|
|
1360
|
+
"composite_rank": 124
|
|
1361
|
+
},
|
|
1362
|
+
{
|
|
1363
|
+
"name": "Grok-4-1-fast-non-reasoning (FC)",
|
|
1364
|
+
"norm": "grok-4-1-fast-non-reasoning",
|
|
1365
|
+
"bfcl_overall": 58.29,
|
|
1366
|
+
"bfcl_multi_turn": 46.75,
|
|
1367
|
+
"bfcl_irrelevance": 74.09,
|
|
1368
|
+
"composite": 0.6995884773662552,
|
|
1369
|
+
"composite_rank": 125
|
|
1370
|
+
},
|
|
1371
|
+
{
|
|
1372
|
+
"name": "glm-4.5",
|
|
1373
|
+
"norm": "glm-4.5",
|
|
1374
|
+
"bfcl_overall": null,
|
|
1375
|
+
"bfcl_multi_turn": null,
|
|
1376
|
+
"bfcl_irrelevance": null,
|
|
1377
|
+
"arena_rating": 1411.0275824992461,
|
|
1378
|
+
"arena_rank": 114,
|
|
1379
|
+
"composite": 0.6970509383378016,
|
|
1380
|
+
"composite_rank": 126
|
|
1381
|
+
},
|
|
1382
|
+
{
|
|
1383
|
+
"name": "mistral-medium-2508",
|
|
1384
|
+
"norm": "mistral-medium-2508",
|
|
1385
|
+
"bfcl_overall": null,
|
|
1386
|
+
"bfcl_multi_turn": null,
|
|
1387
|
+
"bfcl_irrelevance": null,
|
|
1388
|
+
"arena_rating": 1409.5615111145476,
|
|
1389
|
+
"arena_rank": 117,
|
|
1390
|
+
"composite": 0.6890080428954424,
|
|
1391
|
+
"composite_rank": 127
|
|
1392
|
+
},
|
|
1393
|
+
{
|
|
1394
|
+
"name": "qwen3.5-27b",
|
|
1395
|
+
"norm": "qwen3.5-27b",
|
|
1396
|
+
"bfcl_overall": null,
|
|
1397
|
+
"bfcl_multi_turn": null,
|
|
1398
|
+
"bfcl_irrelevance": null,
|
|
1399
|
+
"arena_rating": 1408.6001905823339,
|
|
1400
|
+
"arena_rank": 118,
|
|
1401
|
+
"composite": 0.6863270777479893,
|
|
1402
|
+
"composite_rank": 128
|
|
1403
|
+
},
|
|
1404
|
+
{
|
|
1405
|
+
"name": "gemini-2.5-flash-preview-09-2025",
|
|
1406
|
+
"norm": "gemini-2.5-flash-preview-09-2025",
|
|
1407
|
+
"bfcl_overall": null,
|
|
1408
|
+
"bfcl_multi_turn": null,
|
|
1409
|
+
"bfcl_irrelevance": null,
|
|
1410
|
+
"arena_rating": 1404.4156046588573,
|
|
1411
|
+
"arena_rank": 119,
|
|
1412
|
+
"composite": 0.6836461126005362,
|
|
1413
|
+
"composite_rank": 129
|
|
1414
|
+
},
|
|
1415
|
+
{
|
|
1416
|
+
"name": "Command A (FC)",
|
|
1417
|
+
"norm": "command a",
|
|
1418
|
+
"bfcl_overall": 46.49,
|
|
1419
|
+
"bfcl_multi_turn": 29.5,
|
|
1420
|
+
"bfcl_irrelevance": 84.19,
|
|
1421
|
+
"composite": 0.683127572016461,
|
|
1422
|
+
"composite_rank": 130
|
|
1423
|
+
},
|
|
1424
|
+
{
|
|
1425
|
+
"name": "grok-4-fast-reasoning",
|
|
1426
|
+
"norm": "grok-4-fast-reasoning",
|
|
1427
|
+
"bfcl_overall": null,
|
|
1428
|
+
"bfcl_multi_turn": null,
|
|
1429
|
+
"bfcl_irrelevance": null,
|
|
1430
|
+
"arena_rating": 1404.095296531749,
|
|
1431
|
+
"arena_rank": 120,
|
|
1432
|
+
"composite": 0.6809651474530831,
|
|
1433
|
+
"composite_rank": 131
|
|
1434
|
+
},
|
|
1435
|
+
{
|
|
1436
|
+
"name": "gpt-5.4-nano-high",
|
|
1437
|
+
"norm": "gpt-5.4-nano-high",
|
|
1438
|
+
"bfcl_overall": null,
|
|
1439
|
+
"bfcl_multi_turn": null,
|
|
1440
|
+
"bfcl_irrelevance": null,
|
|
1441
|
+
"arena_rating": 1403.5884796798612,
|
|
1442
|
+
"arena_rank": 121,
|
|
1443
|
+
"composite": 0.67828418230563,
|
|
1444
|
+
"composite_rank": 132
|
|
1445
|
+
},
|
|
1446
|
+
{
|
|
1447
|
+
"name": "Qwen3-235B-A22B-Instruct-2507 (Prompt)",
|
|
1448
|
+
"norm": "qwen3-235b-a22b-instruct-2507",
|
|
1449
|
+
"bfcl_overall": 52.15,
|
|
1450
|
+
"bfcl_multi_turn": 44.62,
|
|
1451
|
+
"bfcl_irrelevance": 78.89,
|
|
1452
|
+
"arena_rating": 1423.245956395019,
|
|
1453
|
+
"arena_rank": 91,
|
|
1454
|
+
"composite": 0.67733260516996,
|
|
1455
|
+
"composite_rank": 133
|
|
1456
|
+
},
|
|
1457
|
+
{
|
|
1458
|
+
"name": "DeepSeek-V3.2-Exp (Prompt + Thinking)",
|
|
1459
|
+
"norm": "deepseek-v3.2-exp",
|
|
1460
|
+
"bfcl_overall": 56.73,
|
|
1461
|
+
"bfcl_multi_turn": 44.88,
|
|
1462
|
+
"bfcl_irrelevance": 67,
|
|
1463
|
+
"arena_rating": 1422.9292447404991,
|
|
1464
|
+
"arena_rank": 93,
|
|
1465
|
+
"composite": 0.6759921225962335,
|
|
1466
|
+
"composite_rank": 134
|
|
1467
|
+
},
|
|
1468
|
+
{
|
|
1469
|
+
"name": "qwen3-235b-a22b-no-thinking",
|
|
1470
|
+
"norm": "qwen3-235b-a22b-no-thinking",
|
|
1471
|
+
"bfcl_overall": null,
|
|
1472
|
+
"bfcl_multi_turn": null,
|
|
1473
|
+
"bfcl_irrelevance": null,
|
|
1474
|
+
"arena_rating": 1403.0944979463166,
|
|
1475
|
+
"arena_rank": 122,
|
|
1476
|
+
"composite": 0.675603217158177,
|
|
1477
|
+
"composite_rank": 135
|
|
1478
|
+
},
|
|
1479
|
+
{
|
|
1480
|
+
"name": "o1-2024-12-17",
|
|
1481
|
+
"norm": "o1-2024-12-17",
|
|
1482
|
+
"bfcl_overall": null,
|
|
1483
|
+
"bfcl_multi_turn": null,
|
|
1484
|
+
"bfcl_irrelevance": null,
|
|
1485
|
+
"arena_rating": 1402.033654210117,
|
|
1486
|
+
"arena_rank": 123,
|
|
1487
|
+
"composite": 0.6729222520107239,
|
|
1488
|
+
"composite_rank": 136
|
|
1489
|
+
},
|
|
1490
|
+
{
|
|
1491
|
+
"name": "Gemini-2.5-Flash-Lite (FC)",
|
|
1492
|
+
"norm": "gemini-2.5-flash-lite",
|
|
1493
|
+
"bfcl_overall": 36.87,
|
|
1494
|
+
"bfcl_multi_turn": 13.5,
|
|
1495
|
+
"bfcl_irrelevance": 92.5,
|
|
1496
|
+
"composite": 0.6707818930041153,
|
|
1497
|
+
"composite_rank": 137
|
|
1498
|
+
},
|
|
1499
|
+
{
|
|
1500
|
+
"name": "qwen3-next-80b-a3b-instruct",
|
|
1501
|
+
"norm": "qwen3-next-80b-a3b-instruct",
|
|
1502
|
+
"bfcl_overall": null,
|
|
1503
|
+
"bfcl_multi_turn": null,
|
|
1504
|
+
"bfcl_irrelevance": null,
|
|
1505
|
+
"arena_rating": 1401.4042663834,
|
|
1506
|
+
"arena_rank": 124,
|
|
1507
|
+
"composite": 0.6702412868632708,
|
|
1508
|
+
"composite_rank": 138
|
|
1509
|
+
},
|
|
1510
|
+
{
|
|
1511
|
+
"name": "longcat-flash-chat",
|
|
1512
|
+
"norm": "longcat-flash-chat",
|
|
1513
|
+
"bfcl_overall": null,
|
|
1514
|
+
"bfcl_multi_turn": null,
|
|
1515
|
+
"bfcl_irrelevance": null,
|
|
1516
|
+
"arena_rating": 1401.168478546817,
|
|
1517
|
+
"arena_rank": 125,
|
|
1518
|
+
"composite": 0.6675603217158177,
|
|
1519
|
+
"composite_rank": 139
|
|
1520
|
+
},
|
|
1521
|
+
{
|
|
1522
|
+
"name": "xLAM-2-70b-fc-r (FC)",
|
|
1523
|
+
"norm": "xlam-2-70b-fc-r",
|
|
1524
|
+
"bfcl_overall": 53.07,
|
|
1525
|
+
"bfcl_multi_turn": 77.38,
|
|
1526
|
+
"bfcl_irrelevance": 79.11,
|
|
1527
|
+
"composite": 0.6666666666666666,
|
|
1528
|
+
"composite_rank": 140
|
|
1529
|
+
},
|
|
1530
|
+
{
|
|
1531
|
+
"name": "claude-sonnet-4-20250514-thinking-32k",
|
|
1532
|
+
"norm": "claude-sonnet-4-20250514-thinking-32k",
|
|
1533
|
+
"bfcl_overall": null,
|
|
1534
|
+
"bfcl_multi_turn": null,
|
|
1535
|
+
"bfcl_irrelevance": null,
|
|
1536
|
+
"arena_rating": 1399.2331526695395,
|
|
1537
|
+
"arena_rank": 126,
|
|
1538
|
+
"composite": 0.6648793565683646,
|
|
1539
|
+
"composite_rank": 141
|
|
1540
|
+
},
|
|
1541
|
+
{
|
|
1542
|
+
"name": "GPT-4.1-mini-2025-04-14 (FC)",
|
|
1543
|
+
"norm": "gpt-4.1-mini-2025-04-14",
|
|
1544
|
+
"bfcl_overall": 50.45,
|
|
1545
|
+
"bfcl_multi_turn": 34.13,
|
|
1546
|
+
"bfcl_irrelevance": 81.69,
|
|
1547
|
+
"arena_rating": 1382.8308849797288,
|
|
1548
|
+
"arena_rank": 149,
|
|
1549
|
+
"composite": 0.6631499685565816,
|
|
1550
|
+
"composite_rank": 142
|
|
1551
|
+
},
|
|
1552
|
+
{
|
|
1553
|
+
"name": "qwen3-235b-a22b-thinking-2507",
|
|
1554
|
+
"norm": "qwen3-235b-a22b-thinking-2507",
|
|
1555
|
+
"bfcl_overall": null,
|
|
1556
|
+
"bfcl_multi_turn": null,
|
|
1557
|
+
"bfcl_irrelevance": null,
|
|
1558
|
+
"arena_rating": 1399.16622442724,
|
|
1559
|
+
"arena_rank": 127,
|
|
1560
|
+
"composite": 0.6621983914209115,
|
|
1561
|
+
"composite_rank": 143
|
|
1562
|
+
},
|
|
1563
|
+
{
|
|
1564
|
+
"name": "deepseek-r1",
|
|
1565
|
+
"norm": "deepseek-r1",
|
|
1566
|
+
"bfcl_overall": null,
|
|
1567
|
+
"bfcl_multi_turn": null,
|
|
1568
|
+
"bfcl_irrelevance": null,
|
|
1569
|
+
"arena_rating": 1398.1249518602772,
|
|
1570
|
+
"arena_rank": 128,
|
|
1571
|
+
"composite": 0.6595174262734584,
|
|
1572
|
+
"composite_rank": 144
|
|
1573
|
+
},
|
|
1574
|
+
{
|
|
1575
|
+
"name": "qwen3.5-flash",
|
|
1576
|
+
"norm": "qwen3.5-flash",
|
|
1577
|
+
"bfcl_overall": null,
|
|
1578
|
+
"bfcl_multi_turn": null,
|
|
1579
|
+
"bfcl_irrelevance": null,
|
|
1580
|
+
"arena_rating": 1397.5720829093445,
|
|
1581
|
+
"arena_rank": 129,
|
|
1582
|
+
"composite": 0.6568364611260054,
|
|
1583
|
+
"composite_rank": 145
|
|
1584
|
+
},
|
|
1585
|
+
{
|
|
1586
|
+
"name": "deepseek-v3-0324",
|
|
1587
|
+
"norm": "deepseek-v3-0324",
|
|
1588
|
+
"bfcl_overall": null,
|
|
1589
|
+
"bfcl_multi_turn": null,
|
|
1590
|
+
"bfcl_irrelevance": null,
|
|
1591
|
+
"arena_rating": 1395.5860688574305,
|
|
1592
|
+
"arena_rank": 130,
|
|
1593
|
+
"composite": 0.6541554959785523,
|
|
1594
|
+
"composite_rank": 146
|
|
1595
|
+
},
|
|
1596
|
+
{
|
|
1597
|
+
"name": "qwen3.5-35b-a3b",
|
|
1598
|
+
"norm": "qwen3.5-35b-a3b",
|
|
1599
|
+
"bfcl_overall": null,
|
|
1600
|
+
"bfcl_multi_turn": null,
|
|
1601
|
+
"bfcl_irrelevance": null,
|
|
1602
|
+
"arena_rating": 1395.5834176813757,
|
|
1603
|
+
"arena_rank": 131,
|
|
1604
|
+
"composite": 0.6514745308310992,
|
|
1605
|
+
"composite_rank": 147
|
|
1606
|
+
},
|
|
1607
|
+
{
|
|
1608
|
+
"name": "qwen3-vl-235b-a22b-thinking",
|
|
1609
|
+
"norm": "qwen3-vl-235b-a22b-thinking",
|
|
1610
|
+
"bfcl_overall": null,
|
|
1611
|
+
"bfcl_multi_turn": null,
|
|
1612
|
+
"bfcl_irrelevance": null,
|
|
1613
|
+
"arena_rating": 1395.548479534433,
|
|
1614
|
+
"arena_rank": 132,
|
|
1615
|
+
"composite": 0.6487935656836461,
|
|
1616
|
+
"composite_rank": 148
|
|
1617
|
+
},
|
|
1618
|
+
{
|
|
1619
|
+
"name": "hunyuan-vision-1.5-thinking",
|
|
1620
|
+
"norm": "hunyuan-vision-1.5-thinking",
|
|
1621
|
+
"bfcl_overall": null,
|
|
1622
|
+
"bfcl_multi_turn": null,
|
|
1623
|
+
"bfcl_irrelevance": null,
|
|
1624
|
+
"arena_rating": 1395.3246624573262,
|
|
1625
|
+
"arena_rank": 133,
|
|
1626
|
+
"composite": 0.646112600536193,
|
|
1627
|
+
"composite_rank": 149
|
|
1628
|
+
},
|
|
1629
|
+
{
|
|
1630
|
+
"name": "Arch-Agent-32B",
|
|
1631
|
+
"norm": "arch-agent-32b",
|
|
1632
|
+
"bfcl_overall": 45.37,
|
|
1633
|
+
"bfcl_multi_turn": 54.25,
|
|
1634
|
+
"bfcl_irrelevance": 82.15,
|
|
1635
|
+
"composite": 0.6460905349794239,
|
|
1636
|
+
"composite_rank": 150
|
|
1637
|
+
},
|
|
1638
|
+
{
|
|
1639
|
+
"name": "step-3.5-flash",
|
|
1640
|
+
"norm": "step-3.5-flash",
|
|
1641
|
+
"bfcl_overall": null,
|
|
1642
|
+
"bfcl_multi_turn": null,
|
|
1643
|
+
"bfcl_irrelevance": null,
|
|
1644
|
+
"arena_rating": 1395.1238802700439,
|
|
1645
|
+
"arena_rank": 134,
|
|
1646
|
+
"composite": 0.6434316353887399,
|
|
1647
|
+
"composite_rank": 151
|
|
1648
|
+
},
|
|
1649
|
+
{
|
|
1650
|
+
"name": "amazon-nova-experimental-chat-12-10",
|
|
1651
|
+
"norm": "amazon-nova-experimental-chat-12-10",
|
|
1652
|
+
"bfcl_overall": null,
|
|
1653
|
+
"bfcl_multi_turn": null,
|
|
1654
|
+
"bfcl_irrelevance": null,
|
|
1655
|
+
"arena_rating": 1394.410029025651,
|
|
1656
|
+
"arena_rank": 135,
|
|
1657
|
+
"composite": 0.6407506702412868,
|
|
1658
|
+
"composite_rank": 152
|
|
1659
|
+
},
|
|
1660
|
+
{
|
|
1661
|
+
"name": "mimo-v2-flash (non-thinking)",
|
|
1662
|
+
"norm": "mimo-v2-flash (non-thinking)",
|
|
1663
|
+
"bfcl_overall": null,
|
|
1664
|
+
"bfcl_multi_turn": null,
|
|
1665
|
+
"bfcl_irrelevance": null,
|
|
1666
|
+
"arena_rating": 1392.9235283333671,
|
|
1667
|
+
"arena_rank": 136,
|
|
1668
|
+
"composite": 0.6380697050938338,
|
|
1669
|
+
"composite_rank": 153
|
|
1670
|
+
},
|
|
1671
|
+
{
|
|
1672
|
+
"name": "minimax-m2.5",
|
|
1673
|
+
"norm": "minimax-m2.5",
|
|
1674
|
+
"bfcl_overall": null,
|
|
1675
|
+
"bfcl_multi_turn": null,
|
|
1676
|
+
"bfcl_irrelevance": null,
|
|
1677
|
+
"arena_rating": 1390.574867628528,
|
|
1678
|
+
"arena_rank": 137,
|
|
1679
|
+
"composite": 0.6353887399463807,
|
|
1680
|
+
"composite_rank": 154
|
|
1681
|
+
},
|
|
1682
|
+
{
|
|
1683
|
+
"name": "gpt-5-mini-high",
|
|
1684
|
+
"norm": "gpt-5-mini-high",
|
|
1685
|
+
"bfcl_overall": null,
|
|
1686
|
+
"bfcl_multi_turn": null,
|
|
1687
|
+
"bfcl_irrelevance": null,
|
|
1688
|
+
"arena_rating": 1390.0045268349315,
|
|
1689
|
+
"arena_rank": 138,
|
|
1690
|
+
"composite": 0.6327077747989276,
|
|
1691
|
+
"composite_rank": 155
|
|
1692
|
+
},
|
|
1693
|
+
{
|
|
1694
|
+
"name": "Mistral-small-2506 (FC)",
|
|
1695
|
+
"norm": "mistral-small-2506",
|
|
1696
|
+
"bfcl_overall": 37.15,
|
|
1697
|
+
"bfcl_multi_turn": 11.5,
|
|
1698
|
+
"bfcl_irrelevance": 87.94,
|
|
1699
|
+
"arena_rating": 1357.6138602907774,
|
|
1700
|
+
"arena_rank": 171,
|
|
1701
|
+
"composite": 0.6298861417270711,
|
|
1702
|
+
"composite_rank": 156
|
|
1703
|
+
},
|
|
1704
|
+
{
|
|
1705
|
+
"name": "claude-sonnet-4-20250514",
|
|
1706
|
+
"norm": "claude-sonnet-4-20250514",
|
|
1707
|
+
"bfcl_overall": null,
|
|
1708
|
+
"bfcl_multi_turn": null,
|
|
1709
|
+
"bfcl_irrelevance": null,
|
|
1710
|
+
"arena_rating": 1389.129160378667,
|
|
1711
|
+
"arena_rank": 140,
|
|
1712
|
+
"composite": 0.6273458445040214,
|
|
1713
|
+
"composite_rank": 157
|
|
1714
|
+
},
|
|
1715
|
+
{
|
|
1716
|
+
"name": "o1-preview",
|
|
1717
|
+
"norm": "o1-preview",
|
|
1718
|
+
"bfcl_overall": null,
|
|
1719
|
+
"bfcl_multi_turn": null,
|
|
1720
|
+
"bfcl_irrelevance": null,
|
|
1721
|
+
"arena_rating": 1388.3541654840285,
|
|
1722
|
+
"arena_rank": 141,
|
|
1723
|
+
"composite": 0.6246648793565683,
|
|
1724
|
+
"composite_rank": 158
|
|
1725
|
+
},
|
|
1726
|
+
{
|
|
1727
|
+
"name": "qwen3-coder-480b-a35b-instruct",
|
|
1728
|
+
"norm": "qwen3-coder-480b-a35b-instruct",
|
|
1729
|
+
"bfcl_overall": null,
|
|
1730
|
+
"bfcl_multi_turn": null,
|
|
1731
|
+
"bfcl_irrelevance": null,
|
|
1732
|
+
"arena_rating": 1387.630707902755,
|
|
1733
|
+
"arena_rank": 142,
|
|
1734
|
+
"composite": 0.6219839142091153,
|
|
1735
|
+
"composite_rank": 159
|
|
1736
|
+
},
|
|
1737
|
+
{
|
|
1738
|
+
"name": "claude-3-7-sonnet-20250219-thinking-32k",
|
|
1739
|
+
"norm": "claude-3-7-sonnet-20250219-thinking-32k",
|
|
1740
|
+
"bfcl_overall": null,
|
|
1741
|
+
"bfcl_multi_turn": null,
|
|
1742
|
+
"bfcl_irrelevance": null,
|
|
1743
|
+
"arena_rating": 1387.2551422082718,
|
|
1744
|
+
"arena_rank": 143,
|
|
1745
|
+
"composite": 0.6193029490616622,
|
|
1746
|
+
"composite_rank": 160
|
|
1747
|
+
},
|
|
1748
|
+
{
|
|
1749
|
+
"name": "mimo-v2-flash (thinking)",
|
|
1750
|
+
"norm": "mimo-v2-flash (thinking)",
|
|
1751
|
+
"bfcl_overall": null,
|
|
1752
|
+
"bfcl_multi_turn": null,
|
|
1753
|
+
"bfcl_irrelevance": null,
|
|
1754
|
+
"arena_rating": 1387.037730461344,
|
|
1755
|
+
"arena_rank": 144,
|
|
1756
|
+
"composite": 0.6166219839142091,
|
|
1757
|
+
"composite_rank": 161
|
|
1758
|
+
},
|
|
1759
|
+
{
|
|
1760
|
+
"name": "hunyuan-t1-20250711",
|
|
1761
|
+
"norm": "hunyuan-t1-20250711",
|
|
1762
|
+
"bfcl_overall": null,
|
|
1763
|
+
"bfcl_multi_turn": null,
|
|
1764
|
+
"bfcl_irrelevance": null,
|
|
1765
|
+
"arena_rating": 1386.9629829032085,
|
|
1766
|
+
"arena_rank": 145,
|
|
1767
|
+
"composite": 0.613941018766756,
|
|
1768
|
+
"composite_rank": 162
|
|
1769
|
+
},
|
|
1770
|
+
{
|
|
1771
|
+
"name": "minimax-m2.1-preview",
|
|
1772
|
+
"norm": "minimax-m2.1-preview",
|
|
1773
|
+
"bfcl_overall": null,
|
|
1774
|
+
"bfcl_multi_turn": null,
|
|
1775
|
+
"bfcl_irrelevance": null,
|
|
1776
|
+
"arena_rating": 1384.4270502381603,
|
|
1777
|
+
"arena_rank": 147,
|
|
1778
|
+
"composite": 0.6085790884718498,
|
|
1779
|
+
"composite_rank": 163
|
|
1780
|
+
},
|
|
1781
|
+
{
|
|
1782
|
+
"name": "Hammer2.1-7b (FC)",
|
|
1783
|
+
"norm": "hammer2.1-7b",
|
|
1784
|
+
"bfcl_overall": 31.67,
|
|
1785
|
+
"bfcl_multi_turn": 23.87,
|
|
1786
|
+
"bfcl_irrelevance": 90.12,
|
|
1787
|
+
"composite": 0.6008230452674898,
|
|
1788
|
+
"composite_rank": 164
|
|
1789
|
+
},
|
|
1790
|
+
{
|
|
1791
|
+
"name": "hunyuan-turbos-20250416",
|
|
1792
|
+
"norm": "hunyuan-turbos-20250416",
|
|
1793
|
+
"bfcl_overall": null,
|
|
1794
|
+
"bfcl_multi_turn": null,
|
|
1795
|
+
"bfcl_irrelevance": null,
|
|
1796
|
+
"arena_rating": 1382.2869538872565,
|
|
1797
|
+
"arena_rank": 150,
|
|
1798
|
+
"composite": 0.6005361930294906,
|
|
1799
|
+
"composite_rank": 165
|
|
1800
|
+
},
|
|
1801
|
+
{
|
|
1802
|
+
"name": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
|
|
1803
|
+
"norm": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
|
|
1804
|
+
"bfcl_overall": null,
|
|
1805
|
+
"bfcl_multi_turn": null,
|
|
1806
|
+
"bfcl_irrelevance": null,
|
|
1807
|
+
"arena_rating": 1379.7217411222734,
|
|
1808
|
+
"arena_rank": 151,
|
|
1809
|
+
"composite": 0.5978552278820375,
|
|
1810
|
+
"composite_rank": 166
|
|
1811
|
+
},
|
|
1812
|
+
{
|
|
1813
|
+
"name": "Qwen3-14B (FC)",
|
|
1814
|
+
"norm": "qwen3-14b",
|
|
1815
|
+
"bfcl_overall": 41.03,
|
|
1816
|
+
"bfcl_multi_turn": 34.75,
|
|
1817
|
+
"bfcl_irrelevance": 81.94,
|
|
1818
|
+
"composite": 0.5967078189300411,
|
|
1819
|
+
"composite_rank": 167
|
|
1820
|
+
},
|
|
1821
|
+
{
|
|
1822
|
+
"name": "trinity-large-preview",
|
|
1823
|
+
"norm": "trinity-large-preview",
|
|
1824
|
+
"bfcl_overall": null,
|
|
1825
|
+
"bfcl_multi_turn": null,
|
|
1826
|
+
"bfcl_irrelevance": null,
|
|
1827
|
+
"arena_rating": 1378.5400033523513,
|
|
1828
|
+
"arena_rank": 152,
|
|
1829
|
+
"composite": 0.5951742627345844,
|
|
1830
|
+
"composite_rank": 168
|
|
1831
|
+
},
|
|
1832
|
+
{
|
|
1833
|
+
"name": "glm-4.6v",
|
|
1834
|
+
"norm": "glm-4.6v",
|
|
1835
|
+
"bfcl_overall": null,
|
|
1836
|
+
"bfcl_multi_turn": null,
|
|
1837
|
+
"bfcl_irrelevance": null,
|
|
1838
|
+
"arena_rating": 1377.198884109575,
|
|
1839
|
+
"arena_rank": 153,
|
|
1840
|
+
"composite": 0.5924932975871313,
|
|
1841
|
+
"composite_rank": 169
|
|
1842
|
+
},
|
|
1843
|
+
{
|
|
1844
|
+
"name": "qwen3-235b-a22b",
|
|
1845
|
+
"norm": "qwen3-235b-a22b",
|
|
1846
|
+
"bfcl_overall": null,
|
|
1847
|
+
"bfcl_multi_turn": null,
|
|
1848
|
+
"bfcl_irrelevance": null,
|
|
1849
|
+
"arena_rating": 1374.7839275575984,
|
|
1850
|
+
"arena_rank": 154,
|
|
1851
|
+
"composite": 0.5898123324396782,
|
|
1852
|
+
"composite_rank": 170
|
|
1853
|
+
},
|
|
1854
|
+
{
|
|
1855
|
+
"name": "Qwen3-4B-Instruct-2507 (FC)",
|
|
1856
|
+
"norm": "qwen3-4b-instruct-2507",
|
|
1857
|
+
"bfcl_overall": 35.68,
|
|
1858
|
+
"bfcl_multi_turn": 22.12,
|
|
1859
|
+
"bfcl_irrelevance": 84.93,
|
|
1860
|
+
"composite": 0.5884773662551441,
|
|
1861
|
+
"composite_rank": 171
|
|
1862
|
+
},
|
|
1863
|
+
{
|
|
1864
|
+
"name": "gemini-2.5-flash-lite-preview-06-17-thinking",
|
|
1865
|
+
"norm": "gemini-2.5-flash-lite-preview-06-17-thinking",
|
|
1866
|
+
"bfcl_overall": null,
|
|
1867
|
+
"bfcl_multi_turn": null,
|
|
1868
|
+
"bfcl_irrelevance": null,
|
|
1869
|
+
"arena_rating": 1374.384735369688,
|
|
1870
|
+
"arena_rank": 155,
|
|
1871
|
+
"composite": 0.5871313672922251,
|
|
1872
|
+
"composite_rank": 172
|
|
1873
|
+
},
|
|
1874
|
+
{
|
|
1875
|
+
"name": "qwen2.5-max",
|
|
1876
|
+
"norm": "qwen2.5-max",
|
|
1877
|
+
"bfcl_overall": null,
|
|
1878
|
+
"bfcl_multi_turn": null,
|
|
1879
|
+
"bfcl_irrelevance": null,
|
|
1880
|
+
"arena_rating": 1374.1906078475802,
|
|
1881
|
+
"arena_rank": 156,
|
|
1882
|
+
"composite": 0.5844504021447721,
|
|
1883
|
+
"composite_rank": 173
|
|
1884
|
+
},
|
|
1885
|
+
{
|
|
1886
|
+
"name": "Qwen3-30B-A3B-Instruct-2507 (FC)",
|
|
1887
|
+
"norm": "qwen3-30b-a3b-instruct-2507",
|
|
1888
|
+
"bfcl_overall": 41.39,
|
|
1889
|
+
"bfcl_multi_turn": 30,
|
|
1890
|
+
"bfcl_irrelevance": 79.9,
|
|
1891
|
+
"arena_rating": 1383.2308866670767,
|
|
1892
|
+
"arena_rank": 148,
|
|
1893
|
+
"composite": 0.583573296263198,
|
|
1894
|
+
"composite_rank": 174
|
|
1895
|
+
},
|
|
1896
|
+
{
|
|
1897
|
+
"name": "Qwen3-32B (FC)",
|
|
1898
|
+
"norm": "qwen3-32b",
|
|
1899
|
+
"bfcl_overall": 48.71,
|
|
1900
|
+
"bfcl_multi_turn": 47.87,
|
|
1901
|
+
"bfcl_irrelevance": 76.37,
|
|
1902
|
+
"arena_rating": 1347.2514108407524,
|
|
1903
|
+
"arena_rank": 186,
|
|
1904
|
+
"composite": 0.582795485387085,
|
|
1905
|
+
"composite_rank": 175
|
|
1906
|
+
},
|
|
1907
|
+
{
|
|
1908
|
+
"name": "glm-4.5-air",
|
|
1909
|
+
"norm": "glm-4.5-air",
|
|
1910
|
+
"bfcl_overall": null,
|
|
1911
|
+
"bfcl_multi_turn": null,
|
|
1912
|
+
"bfcl_irrelevance": null,
|
|
1913
|
+
"arena_rating": 1373.0494215091176,
|
|
1914
|
+
"arena_rank": 157,
|
|
1915
|
+
"composite": 0.581769436997319,
|
|
1916
|
+
"composite_rank": 176
|
|
1917
|
+
},
|
|
1918
|
+
{
|
|
1919
|
+
"name": "Nanbeige3.5-Pro-Thinking (FC)",
|
|
1920
|
+
"norm": "nanbeige3.5-pro-thinking",
|
|
1921
|
+
"bfcl_overall": 47.68,
|
|
1922
|
+
"bfcl_multi_turn": 40,
|
|
1923
|
+
"bfcl_irrelevance": 74.2,
|
|
1924
|
+
"composite": 0.5802469135802469,
|
|
1925
|
+
"composite_rank": 177
|
|
1926
|
+
},
|
|
1927
|
+
{
|
|
1928
|
+
"name": "claude-3-5-sonnet-20241022",
|
|
1929
|
+
"norm": "claude-3-5-sonnet-20241022",
|
|
1930
|
+
"bfcl_overall": null,
|
|
1931
|
+
"bfcl_multi_turn": null,
|
|
1932
|
+
"bfcl_irrelevance": null,
|
|
1933
|
+
"arena_rating": 1372.9354244757437,
|
|
1934
|
+
"arena_rank": 158,
|
|
1935
|
+
"composite": 0.5790884718498659,
|
|
1936
|
+
"composite_rank": 178
|
|
1937
|
+
},
|
|
1938
|
+
{
|
|
1939
|
+
"name": "claude-3-7-sonnet-20250219",
|
|
1940
|
+
"norm": "claude-3-7-sonnet-20250219",
|
|
1941
|
+
"bfcl_overall": null,
|
|
1942
|
+
"bfcl_multi_turn": null,
|
|
1943
|
+
"bfcl_irrelevance": null,
|
|
1944
|
+
"arena_rating": 1371.3500058240645,
|
|
1945
|
+
"arena_rank": 159,
|
|
1946
|
+
"composite": 0.5764075067024128,
|
|
1947
|
+
"composite_rank": 179
|
|
1948
|
+
},
|
|
1949
|
+
{
|
|
1950
|
+
"name": "qwen3-next-80b-a3b-thinking",
|
|
1951
|
+
"norm": "qwen3-next-80b-a3b-thinking",
|
|
1952
|
+
"bfcl_overall": null,
|
|
1953
|
+
"bfcl_multi_turn": null,
|
|
1954
|
+
"bfcl_irrelevance": null,
|
|
1955
|
+
"arena_rating": 1369.6686443052795,
|
|
1956
|
+
"arena_rank": 160,
|
|
1957
|
+
"composite": 0.5737265415549597,
|
|
1958
|
+
"composite_rank": 180
|
|
1959
|
+
},
|
|
1960
|
+
{
|
|
1961
|
+
"name": "Qwen3-8B (FC)",
|
|
1962
|
+
"norm": "qwen3-8b",
|
|
1963
|
+
"bfcl_overall": 42.57,
|
|
1964
|
+
"bfcl_multi_turn": 41.75,
|
|
1965
|
+
"bfcl_irrelevance": 79.07,
|
|
1966
|
+
"composite": 0.5720164609053499,
|
|
1967
|
+
"composite_rank": 181
|
|
1968
|
+
},
|
|
1969
|
+
{
|
|
1970
|
+
"name": "trinity-large-thinking",
|
|
1971
|
+
"norm": "trinity-large-thinking",
|
|
1972
|
+
"bfcl_overall": null,
|
|
1973
|
+
"bfcl_multi_turn": null,
|
|
1974
|
+
"bfcl_irrelevance": null,
|
|
1975
|
+
"arena_rating": 1369.2670494678405,
|
|
1976
|
+
"arena_rank": 161,
|
|
1977
|
+
"composite": 0.5710455764075066,
|
|
1978
|
+
"composite_rank": 182
|
|
1979
|
+
},
|
|
1980
|
+
{
|
|
1981
|
+
"name": "glm-4.7-flash",
|
|
1982
|
+
"norm": "glm-4.7-flash",
|
|
1983
|
+
"bfcl_overall": null,
|
|
1984
|
+
"bfcl_multi_turn": null,
|
|
1985
|
+
"bfcl_irrelevance": null,
|
|
1986
|
+
"arena_rating": 1368.0781191188676,
|
|
1987
|
+
"arena_rank": 162,
|
|
1988
|
+
"composite": 0.5683646112600536,
|
|
1989
|
+
"composite_rank": 183
|
|
1990
|
+
},
|
|
1991
|
+
{
|
|
1992
|
+
"name": "amazon-nova-experimental-chat-11-10",
|
|
1993
|
+
"norm": "amazon-nova-experimental-chat-11-10",
|
|
1994
|
+
"bfcl_overall": null,
|
|
1995
|
+
"bfcl_multi_turn": null,
|
|
1996
|
+
"bfcl_irrelevance": null,
|
|
1997
|
+
"arena_rating": 1366.4516749157822,
|
|
1998
|
+
"arena_rank": 163,
|
|
1999
|
+
"composite": 0.5656836461126005,
|
|
2000
|
+
"composite_rank": 184
|
|
2001
|
+
},
|
|
2002
|
+
{
|
|
2003
|
+
"name": "minimax-m1",
|
|
2004
|
+
"norm": "minimax-m1",
|
|
2005
|
+
"bfcl_overall": null,
|
|
2006
|
+
"bfcl_multi_turn": null,
|
|
2007
|
+
"bfcl_irrelevance": null,
|
|
2008
|
+
"arena_rating": 1363.7805435461808,
|
|
2009
|
+
"arena_rank": 165,
|
|
2010
|
+
"composite": 0.5603217158176943,
|
|
2011
|
+
"composite_rank": 185
|
|
2012
|
+
},
|
|
2013
|
+
{
|
|
2014
|
+
"name": "o3-mini-high",
|
|
2015
|
+
"norm": "o3-mini-high",
|
|
2016
|
+
"bfcl_overall": null,
|
|
2017
|
+
"bfcl_multi_turn": null,
|
|
2018
|
+
"bfcl_irrelevance": null,
|
|
2019
|
+
"arena_rating": 1363.4766254144317,
|
|
2020
|
+
"arena_rank": 166,
|
|
2021
|
+
"composite": 0.5576407506702412,
|
|
2022
|
+
"composite_rank": 186
|
|
2023
|
+
},
|
|
2024
|
+
{
|
|
2025
|
+
"name": "grok-3-mini-high",
|
|
2026
|
+
"norm": "grok-3-mini-high",
|
|
2027
|
+
"bfcl_overall": null,
|
|
2028
|
+
"bfcl_multi_turn": null,
|
|
2029
|
+
"bfcl_irrelevance": null,
|
|
2030
|
+
"arena_rating": 1362.116376968125,
|
|
2031
|
+
"arena_rank": 167,
|
|
2032
|
+
"composite": 0.5549597855227881,
|
|
2033
|
+
"composite_rank": 187
|
|
2034
|
+
},
|
|
2035
|
+
{
|
|
2036
|
+
"name": "nvidia-nemotron-3-super-120b-a12b",
|
|
2037
|
+
"norm": "nvidia-nemotron-3-super-120b-a12b",
|
|
2038
|
+
"bfcl_overall": null,
|
|
2039
|
+
"bfcl_multi_turn": null,
|
|
2040
|
+
"bfcl_irrelevance": null,
|
|
2041
|
+
"arena_rating": 1361.3483462660367,
|
|
2042
|
+
"arena_rank": 168,
|
|
2043
|
+
"composite": 0.552278820375335,
|
|
2044
|
+
"composite_rank": 188
|
|
2045
|
+
},
|
|
2046
|
+
{
|
|
2047
|
+
"name": "gemini-2.0-flash-001",
|
|
2048
|
+
"norm": "gemini-2.0-flash-001",
|
|
2049
|
+
"bfcl_overall": null,
|
|
2050
|
+
"bfcl_multi_turn": null,
|
|
2051
|
+
"bfcl_irrelevance": null,
|
|
2052
|
+
"arena_rating": 1360.3564884783082,
|
|
2053
|
+
"arena_rank": 169,
|
|
2054
|
+
"composite": 0.549597855227882,
|
|
2055
|
+
"composite_rank": 189
|
|
2056
|
+
},
|
|
2057
|
+
{
|
|
2058
|
+
"name": "deepseek-v3",
|
|
2059
|
+
"norm": "deepseek-v3",
|
|
2060
|
+
"bfcl_overall": null,
|
|
2061
|
+
"bfcl_multi_turn": null,
|
|
2062
|
+
"bfcl_irrelevance": null,
|
|
2063
|
+
"arena_rating": 1358.496513926146,
|
|
2064
|
+
"arena_rank": 170,
|
|
2065
|
+
"composite": 0.5469168900804289,
|
|
2066
|
+
"composite_rank": 190
|
|
2067
|
+
},
|
|
2068
|
+
{
|
|
2069
|
+
"name": "grok-3-mini-beta",
|
|
2070
|
+
"norm": "grok-3-mini-beta",
|
|
2071
|
+
"bfcl_overall": null,
|
|
2072
|
+
"bfcl_multi_turn": null,
|
|
2073
|
+
"bfcl_irrelevance": null,
|
|
2074
|
+
"arena_rating": 1356.699350323958,
|
|
2075
|
+
"arena_rank": 172,
|
|
2076
|
+
"composite": 0.5415549597855228,
|
|
2077
|
+
"composite_rank": 191
|
|
2078
|
+
},
|
|
2079
|
+
{
|
|
2080
|
+
"name": "intellect-3",
|
|
2081
|
+
"norm": "intellect-3",
|
|
2082
|
+
"bfcl_overall": null,
|
|
2083
|
+
"bfcl_multi_turn": null,
|
|
2084
|
+
"bfcl_irrelevance": null,
|
|
2085
|
+
"arena_rating": 1356.409406884507,
|
|
2086
|
+
"arena_rank": 173,
|
|
2087
|
+
"composite": 0.5388739946380697,
|
|
2088
|
+
"composite_rank": 192
|
|
2089
|
+
},
|
|
2090
|
+
{
|
|
2091
|
+
"name": "command-a-03-2025",
|
|
2092
|
+
"norm": "command-a-03-2025",
|
|
2093
|
+
"bfcl_overall": null,
|
|
2094
|
+
"bfcl_multi_turn": null,
|
|
2095
|
+
"bfcl_irrelevance": null,
|
|
2096
|
+
"arena_rating": 1353.9516035962115,
|
|
2097
|
+
"arena_rank": 174,
|
|
2098
|
+
"composite": 0.5361930294906166,
|
|
2099
|
+
"composite_rank": 193
|
|
2100
|
+
},
|
|
2101
|
+
{
|
|
2102
|
+
"name": "Hammer2.1-3b (FC)",
|
|
2103
|
+
"norm": "hammer2.1-3b",
|
|
2104
|
+
"bfcl_overall": 29.71,
|
|
2105
|
+
"bfcl_multi_turn": 16.5,
|
|
2106
|
+
"bfcl_irrelevance": 86.12,
|
|
2107
|
+
"composite": 0.5349794238683128,
|
|
2108
|
+
"composite_rank": 194
|
|
2109
|
+
},
|
|
2110
|
+
{
|
|
2111
|
+
"name": "glm-4.5v",
|
|
2112
|
+
"norm": "glm-4.5v",
|
|
2113
|
+
"bfcl_overall": null,
|
|
2114
|
+
"bfcl_multi_turn": null,
|
|
2115
|
+
"bfcl_irrelevance": null,
|
|
2116
|
+
"arena_rating": 1353.5170111669975,
|
|
2117
|
+
"arena_rank": 175,
|
|
2118
|
+
"composite": 0.5335120643431636,
|
|
2119
|
+
"composite_rank": 195
|
|
2120
|
+
},
|
|
2121
|
+
{
|
|
2122
|
+
"name": "gemini-2.0-flash-lite-preview-02-05",
|
|
2123
|
+
"norm": "gemini-2.0-flash-lite-preview-02-05",
|
|
2124
|
+
"bfcl_overall": null,
|
|
2125
|
+
"bfcl_multi_turn": null,
|
|
2126
|
+
"bfcl_irrelevance": null,
|
|
2127
|
+
"arena_rating": 1353.4579306721373,
|
|
2128
|
+
"arena_rank": 176,
|
|
2129
|
+
"composite": 0.5308310991957105,
|
|
2130
|
+
"composite_rank": 196
|
|
2131
|
+
},
|
|
2132
|
+
{
|
|
2133
|
+
"name": "gpt-oss-120b",
|
|
2134
|
+
"norm": "gpt-oss-120b",
|
|
2135
|
+
"bfcl_overall": null,
|
|
2136
|
+
"bfcl_multi_turn": null,
|
|
2137
|
+
"bfcl_irrelevance": null,
|
|
2138
|
+
"arena_rating": 1352.6191266077117,
|
|
2139
|
+
"arena_rank": 177,
|
|
2140
|
+
"composite": 0.5281501340482574,
|
|
2141
|
+
"composite_rank": 197
|
|
2142
|
+
},
|
|
2143
|
+
{
|
|
2144
|
+
"name": "gemini-1.5-pro-002",
|
|
2145
|
+
"norm": "gemini-1.5-pro-002",
|
|
2146
|
+
"bfcl_overall": null,
|
|
2147
|
+
"bfcl_multi_turn": null,
|
|
2148
|
+
"bfcl_irrelevance": null,
|
|
2149
|
+
"arena_rating": 1351.0588758770718,
|
|
2150
|
+
"arena_rank": 178,
|
|
2151
|
+
"composite": 0.5254691689008043,
|
|
2152
|
+
"composite_rank": 198
|
|
2153
|
+
},
|
|
2154
|
+
{
|
|
2155
|
+
"name": "Mistral-Medium-2505",
|
|
2156
|
+
"norm": "mistral-medium-2505",
|
|
2157
|
+
"bfcl_overall": 37.69,
|
|
2158
|
+
"bfcl_multi_turn": 9.88,
|
|
2159
|
+
"bfcl_irrelevance": 74.49,
|
|
2160
|
+
"arena_rating": 1386.9369890483765,
|
|
2161
|
+
"arena_rank": 146,
|
|
2162
|
+
"composite": 0.5231853837751961,
|
|
2163
|
+
"composite_rank": 199
|
|
2164
|
+
},
|
|
2165
|
+
{
|
|
2166
|
+
"name": "amazon-nova-experimental-chat-10-20",
|
|
2167
|
+
"norm": "amazon-nova-experimental-chat-10-20",
|
|
2168
|
+
"bfcl_overall": null,
|
|
2169
|
+
"bfcl_multi_turn": null,
|
|
2170
|
+
"bfcl_irrelevance": null,
|
|
2171
|
+
"arena_rating": 1349.8725822694169,
|
|
2172
|
+
"arena_rank": 179,
|
|
2173
|
+
"composite": 0.5227882037533512,
|
|
2174
|
+
"composite_rank": 200
|
|
2175
|
+
},
|
|
2176
|
+
{
|
|
2177
|
+
"name": "hunyuan-turbos-20250226",
|
|
2178
|
+
"norm": "hunyuan-turbos-20250226",
|
|
2179
|
+
"bfcl_overall": null,
|
|
2180
|
+
"bfcl_multi_turn": null,
|
|
2181
|
+
"bfcl_irrelevance": null,
|
|
2182
|
+
"arena_rating": 1348.8789786626585,
|
|
2183
|
+
"arena_rank": 180,
|
|
2184
|
+
"composite": 0.5201072386058981,
|
|
2185
|
+
"composite_rank": 201
|
|
2186
|
+
},
|
|
2187
|
+
{
|
|
2188
|
+
"name": "xLAM-2-8b-fc-r (FC)",
|
|
2189
|
+
"norm": "xlam-2-8b-fc-r",
|
|
2190
|
+
"bfcl_overall": 46.68,
|
|
2191
|
+
"bfcl_multi_turn": 70,
|
|
2192
|
+
"bfcl_irrelevance": 63.28,
|
|
2193
|
+
"composite": 0.5185185185185185,
|
|
2194
|
+
"composite_rank": 202
|
|
2195
|
+
},
|
|
2196
|
+
{
|
|
2197
|
+
"name": "step-3",
|
|
2198
|
+
"norm": "step-3",
|
|
2199
|
+
"bfcl_overall": null,
|
|
2200
|
+
"bfcl_multi_turn": null,
|
|
2201
|
+
"bfcl_irrelevance": null,
|
|
2202
|
+
"arena_rating": 1348.4172178378324,
|
|
2203
|
+
"arena_rank": 181,
|
|
2204
|
+
"composite": 0.517426273458445,
|
|
2205
|
+
"composite_rank": 203
|
|
2206
|
+
},
|
|
2207
|
+
{
|
|
2208
|
+
"name": "amazon-nova-experimental-chat-10-09",
|
|
2209
|
+
"norm": "amazon-nova-experimental-chat-10-09",
|
|
2210
|
+
"bfcl_overall": null,
|
|
2211
|
+
"bfcl_multi_turn": null,
|
|
2212
|
+
"bfcl_irrelevance": null,
|
|
2213
|
+
"arena_rating": 1347.7788863585945,
|
|
2214
|
+
"arena_rank": 182,
|
|
2215
|
+
"composite": 0.514745308310992,
|
|
2216
|
+
"composite_rank": 204
|
|
2217
|
+
},
|
|
2218
|
+
{
|
|
2219
|
+
"name": "o3-mini",
|
|
2220
|
+
"norm": "o3-mini",
|
|
2221
|
+
"bfcl_overall": null,
|
|
2222
|
+
"bfcl_multi_turn": null,
|
|
2223
|
+
"bfcl_irrelevance": null,
|
|
2224
|
+
"arena_rating": 1347.7340529582702,
|
|
2225
|
+
"arena_rank": 183,
|
|
2226
|
+
"composite": 0.5120643431635389,
|
|
2227
|
+
"composite_rank": 205
|
|
2228
|
+
},
|
|
2229
|
+
{
|
|
2230
|
+
"name": "mercury-2",
|
|
2231
|
+
"norm": "mercury-2",
|
|
2232
|
+
"bfcl_overall": null,
|
|
2233
|
+
"bfcl_multi_turn": null,
|
|
2234
|
+
"bfcl_irrelevance": null,
|
|
2235
|
+
"arena_rating": 1347.5543850678464,
|
|
2236
|
+
"arena_rank": 184,
|
|
2237
|
+
"composite": 0.5093833780160858,
|
|
2238
|
+
"composite_rank": 206
|
|
2239
|
+
},
|
|
2240
|
+
{
|
|
2241
|
+
"name": "Command R7B (FC)",
|
|
2242
|
+
"norm": "command r7b",
|
|
2243
|
+
"bfcl_overall": 32.07,
|
|
2244
|
+
"bfcl_multi_turn": 8.25,
|
|
2245
|
+
"bfcl_irrelevance": 81.65,
|
|
2246
|
+
"composite": 0.5061728395061729,
|
|
2247
|
+
"composite_rank": 207
|
|
2248
|
+
},
|
|
2249
|
+
{
|
|
2250
|
+
"name": "ling-flash-2.0",
|
|
2251
|
+
"norm": "ling-flash-2.0",
|
|
2252
|
+
"bfcl_overall": null,
|
|
2253
|
+
"bfcl_multi_turn": null,
|
|
2254
|
+
"bfcl_irrelevance": null,
|
|
2255
|
+
"arena_rating": 1346.4204145566557,
|
|
2256
|
+
"arena_rank": 187,
|
|
2257
|
+
"composite": 0.5013404825737265,
|
|
2258
|
+
"composite_rank": 208
|
|
2259
|
+
},
|
|
2260
|
+
{
|
|
2261
|
+
"name": "qwen-plus-0125",
|
|
2262
|
+
"norm": "qwen-plus-0125",
|
|
2263
|
+
"bfcl_overall": null,
|
|
2264
|
+
"bfcl_multi_turn": null,
|
|
2265
|
+
"bfcl_irrelevance": null,
|
|
2266
|
+
"arena_rating": 1346.133872142906,
|
|
2267
|
+
"arena_rank": 188,
|
|
2268
|
+
"composite": 0.49865951742627346,
|
|
2269
|
+
"composite_rank": 209
|
|
2270
|
+
},
|
|
2271
|
+
{
|
|
2272
|
+
"name": "minimax-m2",
|
|
2273
|
+
"norm": "minimax-m2",
|
|
2274
|
+
"bfcl_overall": null,
|
|
2275
|
+
"bfcl_multi_turn": null,
|
|
2276
|
+
"bfcl_irrelevance": null,
|
|
2277
|
+
"arena_rating": 1346.0477091430948,
|
|
2278
|
+
"arena_rank": 189,
|
|
2279
|
+
"composite": 0.4959785522788204,
|
|
2280
|
+
"composite_rank": 210
|
|
2281
|
+
},
|
|
2282
|
+
{
|
|
2283
|
+
"name": "gpt-4o-2024-05-13",
|
|
2284
|
+
"norm": "gpt-4o-2024-05-13",
|
|
2285
|
+
"bfcl_overall": null,
|
|
2286
|
+
"bfcl_multi_turn": null,
|
|
2287
|
+
"bfcl_irrelevance": null,
|
|
2288
|
+
"arena_rating": 1345.7557817545753,
|
|
2289
|
+
"arena_rank": 190,
|
|
2290
|
+
"composite": 0.4932975871313673,
|
|
2291
|
+
"composite_rank": 211
|
|
2292
|
+
},
|
|
2293
|
+
{
|
|
2294
|
+
"name": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
|
|
2295
|
+
"norm": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
|
|
2296
|
+
"bfcl_overall": null,
|
|
2297
|
+
"bfcl_multi_turn": null,
|
|
2298
|
+
"bfcl_irrelevance": null,
|
|
2299
|
+
"arena_rating": 1343.2211959631038,
|
|
2300
|
+
"arena_rank": 191,
|
|
2301
|
+
"composite": 0.4906166219839142,
|
|
2302
|
+
"composite_rank": 212
|
|
2303
|
+
},
|
|
2304
|
+
{
|
|
2305
|
+
"name": "CoALM-70B",
|
|
2306
|
+
"norm": "coalm-70b",
|
|
2307
|
+
"bfcl_overall": 27.99,
|
|
2308
|
+
"bfcl_multi_turn": 10.62,
|
|
2309
|
+
"bfcl_irrelevance": 85.65,
|
|
2310
|
+
"composite": 0.48971193415637854,
|
|
2311
|
+
"composite_rank": 213
|
|
2312
|
+
},
|
|
2313
|
+
{
|
|
2314
|
+
"name": "glm-4-plus-0111",
|
|
2315
|
+
"norm": "glm-4-plus-0111",
|
|
2316
|
+
"bfcl_overall": null,
|
|
2317
|
+
"bfcl_multi_turn": null,
|
|
2318
|
+
"bfcl_irrelevance": null,
|
|
2319
|
+
"arena_rating": 1342.8781348724374,
|
|
2320
|
+
"arena_rank": 192,
|
|
2321
|
+
"composite": 0.4879356568364611,
|
|
2322
|
+
"composite_rank": 214
|
|
2323
|
+
},
|
|
2324
|
+
{
|
|
2325
|
+
"name": "claude-3-5-sonnet-20240620",
|
|
2326
|
+
"norm": "claude-3-5-sonnet-20240620",
|
|
2327
|
+
"bfcl_overall": null,
|
|
2328
|
+
"bfcl_multi_turn": null,
|
|
2329
|
+
"bfcl_irrelevance": null,
|
|
2330
|
+
"arena_rating": 1342.405885502086,
|
|
2331
|
+
"arena_rank": 193,
|
|
2332
|
+
"composite": 0.48525469168900803,
|
|
2333
|
+
"composite_rank": 215
|
|
2334
|
+
},
|
|
2335
|
+
{
|
|
2336
|
+
"name": "hunyuan-turbo-0110",
|
|
2337
|
+
"norm": "hunyuan-turbo-0110",
|
|
2338
|
+
"bfcl_overall": null,
|
|
2339
|
+
"bfcl_multi_turn": null,
|
|
2340
|
+
"bfcl_irrelevance": null,
|
|
2341
|
+
"arena_rating": 1340.7080235135033,
|
|
2342
|
+
"arena_rank": 195,
|
|
2343
|
+
"composite": 0.47989276139410186,
|
|
2344
|
+
"composite_rank": 216
|
|
2345
|
+
},
|
|
2346
|
+
{
|
|
2347
|
+
"name": "gpt-5-nano-high",
|
|
2348
|
+
"norm": "gpt-5-nano-high",
|
|
2349
|
+
"bfcl_overall": null,
|
|
2350
|
+
"bfcl_multi_turn": null,
|
|
2351
|
+
"bfcl_irrelevance": null,
|
|
2352
|
+
"arena_rating": 1337.2380146516002,
|
|
2353
|
+
"arena_rank": 196,
|
|
2354
|
+
"composite": 0.4772117962466488,
|
|
2355
|
+
"composite_rank": 217
|
|
2356
|
+
},
|
|
2357
|
+
{
|
|
2358
|
+
"name": "Phi-4 (Prompt)",
|
|
2359
|
+
"norm": "phi-4",
|
|
2360
|
+
"bfcl_overall": 28.79,
|
|
2361
|
+
"bfcl_multi_turn": 3.88,
|
|
2362
|
+
"bfcl_irrelevance": 87.55,
|
|
2363
|
+
"arena_rating": 1256.0197984936538,
|
|
2364
|
+
"arena_rank": 278,
|
|
2365
|
+
"composite": 0.47483699069936786,
|
|
2366
|
+
"composite_rank": 218
|
|
2367
|
+
},
|
|
2368
|
+
{
|
|
2369
|
+
"name": "o1-mini",
|
|
2370
|
+
"norm": "o1-mini",
|
|
2371
|
+
"bfcl_overall": null,
|
|
2372
|
+
"bfcl_multi_turn": null,
|
|
2373
|
+
"bfcl_irrelevance": null,
|
|
2374
|
+
"arena_rating": 1337.0549403048494,
|
|
2375
|
+
"arena_rank": 197,
|
|
2376
|
+
"composite": 0.4745308310991957,
|
|
2377
|
+
"composite_rank": 219
|
|
2378
|
+
},
|
|
2379
|
+
{
|
|
2380
|
+
"name": "nova-2-lite",
|
|
2381
|
+
"norm": "nova-2-lite",
|
|
2382
|
+
"bfcl_overall": null,
|
|
2383
|
+
"bfcl_multi_turn": null,
|
|
2384
|
+
"bfcl_irrelevance": null,
|
|
2385
|
+
"arena_rating": 1336.996133915525,
|
|
2386
|
+
"arena_rank": 198,
|
|
2387
|
+
"composite": 0.4718498659517426,
|
|
2388
|
+
"composite_rank": 220
|
|
2389
|
+
},
|
|
2390
|
+
{
|
|
2391
|
+
"name": "qwq-32b",
|
|
2392
|
+
"norm": "qwq-32b",
|
|
2393
|
+
"bfcl_overall": null,
|
|
2394
|
+
"bfcl_multi_turn": null,
|
|
2395
|
+
"bfcl_irrelevance": null,
|
|
2396
|
+
"arena_rating": 1336.182820290693,
|
|
2397
|
+
"arena_rank": 199,
|
|
2398
|
+
"composite": 0.4691689008042895,
|
|
2399
|
+
"composite_rank": 221
|
|
2400
|
+
},
|
|
2401
|
+
{
|
|
2402
|
+
"name": "grok-2-2024-08-13",
|
|
2403
|
+
"norm": "grok-2-2024-08-13",
|
|
2404
|
+
"bfcl_overall": null,
|
|
2405
|
+
"bfcl_multi_turn": null,
|
|
2406
|
+
"bfcl_irrelevance": null,
|
|
2407
|
+
"arena_rating": 1335.5963893372075,
|
|
2408
|
+
"arena_rank": 200,
|
|
2409
|
+
"composite": 0.46648793565683644,
|
|
2410
|
+
"composite_rank": 222
|
|
2411
|
+
},
|
|
2412
|
+
{
|
|
2413
|
+
"name": "xLAM-2-3b-fc-r (FC)",
|
|
2414
|
+
"norm": "xlam-2-3b-fc-r",
|
|
2415
|
+
"bfcl_overall": 41.22,
|
|
2416
|
+
"bfcl_multi_turn": 58.38,
|
|
2417
|
+
"bfcl_irrelevance": 63.45,
|
|
2418
|
+
"composite": 0.46502057613168724,
|
|
2419
|
+
"composite_rank": 223
|
|
2420
|
+
},
|
|
2421
|
+
{
|
|
2422
|
+
"name": "gemini-advanced-0514",
|
|
2423
|
+
"norm": "gemini-advanced-0514",
|
|
2424
|
+
"bfcl_overall": null,
|
|
2425
|
+
"bfcl_multi_turn": null,
|
|
2426
|
+
"bfcl_irrelevance": null,
|
|
2427
|
+
"arena_rating": 1335.3190507837435,
|
|
2428
|
+
"arena_rank": 201,
|
|
2429
|
+
"composite": 0.46380697050938335,
|
|
2430
|
+
"composite_rank": 224
|
|
2431
|
+
},
|
|
2432
|
+
{
|
|
2433
|
+
"name": "gpt-4o-2024-08-06",
|
|
2434
|
+
"norm": "gpt-4o-2024-08-06",
|
|
2435
|
+
"bfcl_overall": null,
|
|
2436
|
+
"bfcl_multi_turn": null,
|
|
2437
|
+
"bfcl_irrelevance": null,
|
|
2438
|
+
"arena_rating": 1335.0715302062488,
|
|
2439
|
+
"arena_rank": 202,
|
|
2440
|
+
"composite": 0.46112600536193027,
|
|
2441
|
+
"composite_rank": 225
|
|
2442
|
+
},
|
|
2443
|
+
{
|
|
2444
|
+
"name": "llama-3.1-405b-instruct-bf16",
|
|
2445
|
+
"norm": "llama-3.1-405b-instruct-bf16",
|
|
2446
|
+
"bfcl_overall": null,
|
|
2447
|
+
"bfcl_multi_turn": null,
|
|
2448
|
+
"bfcl_irrelevance": null,
|
|
2449
|
+
"arena_rating": 1334.7925319016906,
|
|
2450
|
+
"arena_rank": 203,
|
|
2451
|
+
"composite": 0.4584450402144772,
|
|
2452
|
+
"composite_rank": 226
|
|
2453
|
+
},
|
|
2454
|
+
{
|
|
2455
|
+
"name": "Arch-Agent-3B",
|
|
2456
|
+
"norm": "arch-agent-3b",
|
|
2457
|
+
"bfcl_overall": 35.36,
|
|
2458
|
+
"bfcl_multi_turn": 34.88,
|
|
2459
|
+
"bfcl_irrelevance": 74.67,
|
|
2460
|
+
"composite": 0.45679012345679015,
|
|
2461
|
+
"composite_rank": 227
|
|
2462
|
+
},
|
|
2463
|
+
{
|
|
2464
|
+
"name": "step-2-16k-exp-202412",
|
|
2465
|
+
"norm": "step-2-16k-exp-202412",
|
|
2466
|
+
"bfcl_overall": null,
|
|
2467
|
+
"bfcl_multi_turn": null,
|
|
2468
|
+
"bfcl_irrelevance": null,
|
|
2469
|
+
"arena_rating": 1333.9178139352837,
|
|
2470
|
+
"arena_rank": 204,
|
|
2471
|
+
"composite": 0.4557640750670241,
|
|
2472
|
+
"composite_rank": 228
|
|
2473
|
+
},
|
|
2474
|
+
{
|
|
2475
|
+
"name": "llama-3.1-405b-instruct-fp8",
|
|
2476
|
+
"norm": "llama-3.1-405b-instruct-fp8",
|
|
2477
|
+
"bfcl_overall": null,
|
|
2478
|
+
"bfcl_multi_turn": null,
|
|
2479
|
+
"bfcl_irrelevance": null,
|
|
2480
|
+
"arena_rating": 1332.9576781770159,
|
|
2481
|
+
"arena_rank": 205,
|
|
2482
|
+
"composite": 0.453083109919571,
|
|
2483
|
+
"composite_rank": 229
|
|
2484
|
+
},
|
|
2485
|
+
{
|
|
2486
|
+
"name": "olmo-3.1-32b-instruct",
|
|
2487
|
+
"norm": "olmo-3.1-32b-instruct",
|
|
2488
|
+
"bfcl_overall": null,
|
|
2489
|
+
"bfcl_multi_turn": null,
|
|
2490
|
+
"bfcl_irrelevance": null,
|
|
2491
|
+
"arena_rating": 1330.1363159406899,
|
|
2492
|
+
"arena_rank": 206,
|
|
2493
|
+
"composite": 0.45040214477211793,
|
|
2494
|
+
"composite_rank": 230
|
|
2495
|
+
},
|
|
2496
|
+
{
|
|
2497
|
+
"name": "yi-lightning",
|
|
2498
|
+
"norm": "yi-lightning",
|
|
2499
|
+
"bfcl_overall": null,
|
|
2500
|
+
"bfcl_multi_turn": null,
|
|
2501
|
+
"bfcl_irrelevance": null,
|
|
2502
|
+
"arena_rating": 1328.3109996376627,
|
|
2503
|
+
"arena_rank": 207,
|
|
2504
|
+
"composite": 0.44772117962466484,
|
|
2505
|
+
"composite_rank": 231
|
|
2506
|
+
},
|
|
2507
|
+
{
|
|
2508
|
+
"name": "llama-3.3-nemotron-49b-super-v1",
|
|
2509
|
+
"norm": "llama-3.3-nemotron-49b-super-v1",
|
|
2510
|
+
"bfcl_overall": null,
|
|
2511
|
+
"bfcl_multi_turn": null,
|
|
2512
|
+
"bfcl_irrelevance": null,
|
|
2513
|
+
"arena_rating": 1327.9963596411162,
|
|
2514
|
+
"arena_rank": 208,
|
|
2515
|
+
"composite": 0.44504021447721176,
|
|
2516
|
+
"composite_rank": 232
|
|
2517
|
+
},
|
|
2518
|
+
{
|
|
2519
|
+
"name": "Arch-Agent-1.5B",
|
|
2520
|
+
"norm": "arch-agent-1.5b",
|
|
2521
|
+
"bfcl_overall": 32.14,
|
|
2522
|
+
"bfcl_multi_turn": 26.62,
|
|
2523
|
+
"bfcl_irrelevance": 74.83,
|
|
2524
|
+
"composite": 0.4444444444444445,
|
|
2525
|
+
"composite_rank": 233
|
|
2526
|
+
},
|
|
2527
|
+
{
|
|
2528
|
+
"name": "CoALM-8B",
|
|
2529
|
+
"norm": "coalm-8b",
|
|
2530
|
+
"bfcl_overall": 26.81,
|
|
2531
|
+
"bfcl_multi_turn": 8,
|
|
2532
|
+
"bfcl_irrelevance": 86.9,
|
|
2533
|
+
"composite": 0.4444444444444444,
|
|
2534
|
+
"composite_rank": 234
|
|
2535
|
+
},
|
|
2536
|
+
{
|
|
2537
|
+
"name": "molmo-2-8b",
|
|
2538
|
+
"norm": "molmo-2-8b",
|
|
2539
|
+
"bfcl_overall": null,
|
|
2540
|
+
"bfcl_multi_turn": null,
|
|
2541
|
+
"bfcl_irrelevance": null,
|
|
2542
|
+
"arena_rating": 1327.9476763379007,
|
|
2543
|
+
"arena_rank": 209,
|
|
2544
|
+
"composite": 0.4423592493297587,
|
|
2545
|
+
"composite_rank": 235
|
|
2546
|
+
},
|
|
2547
|
+
{
|
|
2548
|
+
"name": "qwen3-30b-a3b",
|
|
2549
|
+
"norm": "qwen3-30b-a3b",
|
|
2550
|
+
"bfcl_overall": null,
|
|
2551
|
+
"bfcl_multi_turn": null,
|
|
2552
|
+
"bfcl_irrelevance": null,
|
|
2553
|
+
"arena_rating": 1327.2583834501495,
|
|
2554
|
+
"arena_rank": 210,
|
|
2555
|
+
"composite": 0.4396782841823056,
|
|
2556
|
+
"composite_rank": 236
|
|
2557
|
+
},
|
|
2558
|
+
{
|
|
2559
|
+
"name": "mistral-large-2411 (FC)",
|
|
2560
|
+
"norm": "mistral-large-2411",
|
|
2561
|
+
"bfcl_overall": 38.37,
|
|
2562
|
+
"bfcl_multi_turn": 14.12,
|
|
2563
|
+
"bfcl_irrelevance": 68.92,
|
|
2564
|
+
"arena_rating": 1305.2711394135288,
|
|
2565
|
+
"arena_rank": 242,
|
|
2566
|
+
"composite": 0.4372372819647172,
|
|
2567
|
+
"composite_rank": 237
|
|
2568
|
+
},
|
|
2569
|
+
{
|
|
2570
|
+
"name": "llama-4-maverick-17b-128e-instruct",
|
|
2571
|
+
"norm": "llama-4-maverick-17b-128e-instruct",
|
|
2572
|
+
"bfcl_overall": null,
|
|
2573
|
+
"bfcl_multi_turn": null,
|
|
2574
|
+
"bfcl_irrelevance": null,
|
|
2575
|
+
"arena_rating": 1327.0204243726396,
|
|
2576
|
+
"arena_rank": 211,
|
|
2577
|
+
"composite": 0.4369973190348525,
|
|
2578
|
+
"composite_rank": 238
|
|
2579
|
+
},
|
|
2580
|
+
{
|
|
2581
|
+
"name": "hunyuan-large-2025-02-10",
|
|
2582
|
+
"norm": "hunyuan-large-2025-02-10",
|
|
2583
|
+
"bfcl_overall": null,
|
|
2584
|
+
"bfcl_multi_turn": null,
|
|
2585
|
+
"bfcl_irrelevance": null,
|
|
2586
|
+
"arena_rating": 1326.1978986572672,
|
|
2587
|
+
"arena_rank": 212,
|
|
2588
|
+
"composite": 0.4343163538873994,
|
|
2589
|
+
"composite_rank": 239
|
|
2590
|
+
},
|
|
2591
|
+
{
|
|
2592
|
+
"name": "gpt-4-turbo-2024-04-09",
|
|
2593
|
+
"norm": "gpt-4-turbo-2024-04-09",
|
|
2594
|
+
"bfcl_overall": null,
|
|
2595
|
+
"bfcl_multi_turn": null,
|
|
2596
|
+
"bfcl_irrelevance": null,
|
|
2597
|
+
"arena_rating": 1323.969887389297,
|
|
2598
|
+
"arena_rank": 213,
|
|
2599
|
+
"composite": 0.43163538873994634,
|
|
2600
|
+
"composite_rank": 240
|
|
2601
|
+
},
|
|
2602
|
+
{
|
|
2603
|
+
"name": "claude-3-5-haiku-20241022",
|
|
2604
|
+
"norm": "claude-3-5-haiku-20241022",
|
|
2605
|
+
"bfcl_overall": null,
|
|
2606
|
+
"bfcl_multi_turn": null,
|
|
2607
|
+
"bfcl_irrelevance": null,
|
|
2608
|
+
"arena_rating": 1323.6947709612527,
|
|
2609
|
+
"arena_rank": 214,
|
|
2610
|
+
"composite": 0.42895442359249325,
|
|
2611
|
+
"composite_rank": 241
|
|
2612
|
+
},
|
|
2613
|
+
{
|
|
2614
|
+
"name": "gemini-1.5-pro-001",
|
|
2615
|
+
"norm": "gemini-1.5-pro-001",
|
|
2616
|
+
"bfcl_overall": null,
|
|
2617
|
+
"bfcl_multi_turn": null,
|
|
2618
|
+
"bfcl_irrelevance": null,
|
|
2619
|
+
"arena_rating": 1323.6008896320482,
|
|
2620
|
+
"arena_rank": 215,
|
|
2621
|
+
"composite": 0.42627345844504017,
|
|
2622
|
+
"composite_rank": 242
|
|
2623
|
+
},
|
|
2624
|
+
{
|
|
2625
|
+
"name": "deepseek-v2.5-1210",
|
|
2626
|
+
"norm": "deepseek-v2.5-1210",
|
|
2627
|
+
"bfcl_overall": null,
|
|
2628
|
+
"bfcl_multi_turn": null,
|
|
2629
|
+
"bfcl_irrelevance": null,
|
|
2630
|
+
"arena_rating": 1323.4438598628599,
|
|
2631
|
+
"arena_rank": 216,
|
|
2632
|
+
"composite": 0.4235924932975871,
|
|
2633
|
+
"composite_rank": 243
|
|
2634
|
+
},
|
|
2635
|
+
{
|
|
2636
|
+
"name": "Llama-4-Maverick-17B-128E-Instruct-FP8 (FC)",
|
|
2637
|
+
"norm": "llama-4-maverick-17b-128e-instruct-fp8",
|
|
2638
|
+
"bfcl_overall": 37.29,
|
|
2639
|
+
"bfcl_multi_turn": 20.25,
|
|
2640
|
+
"bfcl_irrelevance": 55.97,
|
|
2641
|
+
"composite": 0.4156378600823046,
|
|
2642
|
+
"composite_rank": 244
|
|
2643
|
+
},
|
|
2644
|
+
{
|
|
2645
|
+
"name": "claude-3-opus-20240229",
|
|
2646
|
+
"norm": "claude-3-opus-20240229",
|
|
2647
|
+
"bfcl_overall": null,
|
|
2648
|
+
"bfcl_multi_turn": null,
|
|
2649
|
+
"bfcl_irrelevance": null,
|
|
2650
|
+
"arena_rating": 1321.4011181385117,
|
|
2651
|
+
"arena_rank": 219,
|
|
2652
|
+
"composite": 0.41554959785522794,
|
|
2653
|
+
"composite_rank": 245
|
|
2654
|
+
},
|
|
2655
|
+
{
|
|
2656
|
+
"name": "ring-flash-2.0",
|
|
2657
|
+
"norm": "ring-flash-2.0",
|
|
2658
|
+
"bfcl_overall": null,
|
|
2659
|
+
"bfcl_multi_turn": null,
|
|
2660
|
+
"bfcl_irrelevance": null,
|
|
2661
|
+
"arena_rating": 1320.723002927865,
|
|
2662
|
+
"arena_rank": 220,
|
|
2663
|
+
"composite": 0.41286863270777485,
|
|
2664
|
+
"composite_rank": 246
|
|
2665
|
+
},
|
|
2666
|
+
{
|
|
2667
|
+
"name": "Gemma-3-27b-it (Prompt)",
|
|
2668
|
+
"norm": "gemma-3-27b-it",
|
|
2669
|
+
"bfcl_overall": 29.47,
|
|
2670
|
+
"bfcl_multi_turn": 10.75,
|
|
2671
|
+
"bfcl_irrelevance": 73.67,
|
|
2672
|
+
"arena_rating": 1365.7909876434912,
|
|
2673
|
+
"arena_rank": 164,
|
|
2674
|
+
"composite": 0.41235560851289177,
|
|
2675
|
+
"composite_rank": 247
|
|
2676
|
+
},
|
|
2677
|
+
{
|
|
2678
|
+
"name": "step-1o-turbo-202506",
|
|
2679
|
+
"norm": "step-1o-turbo-202506",
|
|
2680
|
+
"bfcl_overall": null,
|
|
2681
|
+
"bfcl_multi_turn": null,
|
|
2682
|
+
"bfcl_irrelevance": null,
|
|
2683
|
+
"arena_rating": 1320.247882920511,
|
|
2684
|
+
"arena_rank": 221,
|
|
2685
|
+
"composite": 0.41018766756032177,
|
|
2686
|
+
"composite_rank": 248
|
|
2687
|
+
},
|
|
2688
|
+
{
|
|
2689
|
+
"name": "glm-4-plus",
|
|
2690
|
+
"norm": "glm-4-plus",
|
|
2691
|
+
"bfcl_overall": null,
|
|
2692
|
+
"bfcl_multi_turn": null,
|
|
2693
|
+
"bfcl_irrelevance": null,
|
|
2694
|
+
"arena_rating": 1319.3700302622353,
|
|
2695
|
+
"arena_rank": 222,
|
|
2696
|
+
"composite": 0.4075067024128687,
|
|
2697
|
+
"composite_rank": 249
|
|
2698
|
+
},
|
|
2699
|
+
{
|
|
2700
|
+
"name": "GPT-4.1-nano-2025-04-14 (FC)",
|
|
2701
|
+
"norm": "gpt-4.1-nano-2025-04-14",
|
|
2702
|
+
"bfcl_overall": 33.05,
|
|
2703
|
+
"bfcl_multi_turn": 23.62,
|
|
2704
|
+
"bfcl_irrelevance": 66,
|
|
2705
|
+
"arena_rating": 1322.0948220850003,
|
|
2706
|
+
"arena_rank": 218,
|
|
2707
|
+
"composite": 0.4039403568000529,
|
|
2708
|
+
"composite_rank": 250
|
|
2709
|
+
},
|
|
2710
|
+
{
|
|
2711
|
+
"name": "palmyra-x-004 (FC)",
|
|
2712
|
+
"norm": "palmyra-x-004",
|
|
2713
|
+
"bfcl_overall": 27.87,
|
|
2714
|
+
"bfcl_multi_turn": 0.38,
|
|
2715
|
+
"bfcl_irrelevance": 80.99,
|
|
2716
|
+
"composite": 0.40329218106995884,
|
|
2717
|
+
"composite_rank": 251
|
|
2718
|
+
},
|
|
2719
|
+
{
|
|
2720
|
+
"name": "Amazon-Nova-2-Lite-v1:0 (FC)",
|
|
2721
|
+
"norm": "amazon-nova-2-lite-v1:0",
|
|
2722
|
+
"bfcl_overall": 27.1,
|
|
2723
|
+
"bfcl_multi_turn": 2.12,
|
|
2724
|
+
"bfcl_irrelevance": 82.11,
|
|
2725
|
+
"composite": 0.40329218106995884,
|
|
2726
|
+
"composite_rank": 252
|
|
2727
|
+
},
|
|
2728
|
+
{
|
|
2729
|
+
"name": "gemma-3n-e4b-it",
|
|
2730
|
+
"norm": "gemma-3n-e4b-it",
|
|
2731
|
+
"bfcl_overall": null,
|
|
2732
|
+
"bfcl_multi_turn": null,
|
|
2733
|
+
"bfcl_irrelevance": null,
|
|
2734
|
+
"arena_rating": 1318.0881859799133,
|
|
2735
|
+
"arena_rank": 224,
|
|
2736
|
+
"composite": 0.4021447721179625,
|
|
2737
|
+
"composite_rank": 253
|
|
2738
|
+
},
|
|
2739
|
+
{
|
|
2740
|
+
"name": "qwen-max-0919",
|
|
2741
|
+
"norm": "qwen-max-0919",
|
|
2742
|
+
"bfcl_overall": null,
|
|
2743
|
+
"bfcl_multi_turn": null,
|
|
2744
|
+
"bfcl_irrelevance": null,
|
|
2745
|
+
"arena_rating": 1317.9587573931235,
|
|
2746
|
+
"arena_rank": 225,
|
|
2747
|
+
"composite": 0.3994638069705094,
|
|
2748
|
+
"composite_rank": 254
|
|
2749
|
+
},
|
|
2750
|
+
{
|
|
2751
|
+
"name": "gpt-4o-mini-2024-07-18",
|
|
2752
|
+
"norm": "gpt-4o-mini-2024-07-18",
|
|
2753
|
+
"bfcl_overall": null,
|
|
2754
|
+
"bfcl_multi_turn": null,
|
|
2755
|
+
"bfcl_irrelevance": null,
|
|
2756
|
+
"arena_rating": 1317.6925793405906,
|
|
2757
|
+
"arena_rank": 226,
|
|
2758
|
+
"composite": 0.39678284182305634,
|
|
2759
|
+
"composite_rank": 255
|
|
2760
|
+
},
|
|
2761
|
+
{
|
|
2762
|
+
"name": "Gemma-3-12b-it (Prompt)",
|
|
2763
|
+
"norm": "gemma-3-12b-it",
|
|
2764
|
+
"bfcl_overall": 30.43,
|
|
2765
|
+
"bfcl_multi_turn": 5.75,
|
|
2766
|
+
"bfcl_irrelevance": 70.29,
|
|
2767
|
+
"arena_rating": 1341.9150246338122,
|
|
2768
|
+
"arena_rank": 194,
|
|
2769
|
+
"composite": 0.39533478966008007,
|
|
2770
|
+
"composite_rank": 256
|
|
2771
|
+
},
|
|
2772
|
+
{
|
|
2773
|
+
"name": "gpt-oss-20b",
|
|
2774
|
+
"norm": "gpt-oss-20b",
|
|
2775
|
+
"bfcl_overall": null,
|
|
2776
|
+
"bfcl_multi_turn": null,
|
|
2777
|
+
"bfcl_irrelevance": null,
|
|
2778
|
+
"arena_rating": 1317.2761889310852,
|
|
2779
|
+
"arena_rank": 227,
|
|
2780
|
+
"composite": 0.39410187667560326,
|
|
2781
|
+
"composite_rank": 257
|
|
2782
|
+
},
|
|
2783
|
+
{
|
|
2784
|
+
"name": "nvidia-nemotron-3-nano-30b-a3b-bf16",
|
|
2785
|
+
"norm": "nvidia-nemotron-3-nano-30b-a3b-bf16",
|
|
2786
|
+
"bfcl_overall": null,
|
|
2787
|
+
"bfcl_multi_turn": null,
|
|
2788
|
+
"bfcl_irrelevance": null,
|
|
2789
|
+
"arena_rating": 1315.8806943632187,
|
|
2790
|
+
"arena_rank": 228,
|
|
2791
|
+
"composite": 0.3914209115281502,
|
|
2792
|
+
"composite_rank": 258
|
|
2793
|
+
},
|
|
2794
|
+
{
|
|
2795
|
+
"name": "qwen2.5-plus-1127",
|
|
2796
|
+
"norm": "qwen2.5-plus-1127",
|
|
2797
|
+
"bfcl_overall": null,
|
|
2798
|
+
"bfcl_multi_turn": null,
|
|
2799
|
+
"bfcl_irrelevance": null,
|
|
2800
|
+
"arena_rating": 1314.906477823552,
|
|
2801
|
+
"arena_rank": 229,
|
|
2802
|
+
"composite": 0.3887399463806971,
|
|
2803
|
+
"composite_rank": 259
|
|
2804
|
+
},
|
|
2805
|
+
{
|
|
2806
|
+
"name": "athene-v2-chat",
|
|
2807
|
+
"norm": "athene-v2-chat",
|
|
2808
|
+
"bfcl_overall": null,
|
|
2809
|
+
"bfcl_multi_turn": null,
|
|
2810
|
+
"bfcl_irrelevance": null,
|
|
2811
|
+
"arena_rating": 1314.2987637130711,
|
|
2812
|
+
"arena_rank": 230,
|
|
2813
|
+
"composite": 0.386058981233244,
|
|
2814
|
+
"composite_rank": 260
|
|
2815
|
+
},
|
|
2816
|
+
{
|
|
2817
|
+
"name": "mistral-large-2407",
|
|
2818
|
+
"norm": "mistral-large-2407",
|
|
2819
|
+
"bfcl_overall": null,
|
|
2820
|
+
"bfcl_multi_turn": null,
|
|
2821
|
+
"bfcl_irrelevance": null,
|
|
2822
|
+
"arena_rating": 1313.994950279209,
|
|
2823
|
+
"arena_rank": 231,
|
|
2824
|
+
"composite": 0.3833780160857909,
|
|
2825
|
+
"composite_rank": 261
|
|
2826
|
+
},
|
|
2827
|
+
{
|
|
2828
|
+
"name": "Qwen3-1.7B (FC)",
|
|
2829
|
+
"norm": "qwen3-1.7b",
|
|
2830
|
+
"bfcl_overall": 28.41,
|
|
2831
|
+
"bfcl_multi_turn": 11,
|
|
2832
|
+
"bfcl_irrelevance": 76.54,
|
|
2833
|
+
"composite": 0.38271604938271603,
|
|
2834
|
+
"composite_rank": 262
|
|
2835
|
+
},
|
|
2836
|
+
{
|
|
2837
|
+
"name": "gpt-4-0125-preview",
|
|
2838
|
+
"norm": "gpt-4-0125-preview",
|
|
2839
|
+
"bfcl_overall": null,
|
|
2840
|
+
"bfcl_multi_turn": null,
|
|
2841
|
+
"bfcl_irrelevance": null,
|
|
2842
|
+
"arena_rating": 1312.7098955096128,
|
|
2843
|
+
"arena_rank": 232,
|
|
2844
|
+
"composite": 0.38069705093833783,
|
|
2845
|
+
"composite_rank": 263
|
|
2846
|
+
},
|
|
2847
|
+
{
|
|
2848
|
+
"name": "Llama-3.1-Nemotron-Ultra-253B-v1 (FC)",
|
|
2849
|
+
"norm": "llama-3.1-nemotron-ultra-253b-v1",
|
|
2850
|
+
"bfcl_overall": 10,
|
|
2851
|
+
"bfcl_multi_turn": 0,
|
|
2852
|
+
"bfcl_irrelevance": 100,
|
|
2853
|
+
"arena_rating": 1347.484271286217,
|
|
2854
|
+
"arena_rank": 185,
|
|
2855
|
+
"composite": 0.37976202297024464,
|
|
2856
|
+
"composite_rank": 264
|
|
2857
|
+
},
|
|
2858
|
+
{
|
|
2859
|
+
"name": "gpt-4-1106-preview",
|
|
2860
|
+
"norm": "gpt-4-1106-preview",
|
|
2861
|
+
"bfcl_overall": null,
|
|
2862
|
+
"bfcl_multi_turn": null,
|
|
2863
|
+
"bfcl_irrelevance": null,
|
|
2864
|
+
"arena_rating": 1312.2873954867243,
|
|
2865
|
+
"arena_rank": 233,
|
|
2866
|
+
"composite": 0.37801608579088475,
|
|
2867
|
+
"composite_rank": 265
|
|
2868
|
+
},
|
|
2869
|
+
{
|
|
2870
|
+
"name": "hunyuan-standard-2025-02-10",
|
|
2871
|
+
"norm": "hunyuan-standard-2025-02-10",
|
|
2872
|
+
"bfcl_overall": null,
|
|
2873
|
+
"bfcl_multi_turn": null,
|
|
2874
|
+
"bfcl_irrelevance": null,
|
|
2875
|
+
"arena_rating": 1311.1580190505956,
|
|
2876
|
+
"arena_rank": 234,
|
|
2877
|
+
"composite": 0.37533512064343166,
|
|
2878
|
+
"composite_rank": 266
|
|
2879
|
+
},
|
|
2880
|
+
{
|
|
2881
|
+
"name": "Hammer2.1-1.5b (FC)",
|
|
2882
|
+
"norm": "hammer2.1-1.5b",
|
|
2883
|
+
"bfcl_overall": 27.88,
|
|
2884
|
+
"bfcl_multi_turn": 15.62,
|
|
2885
|
+
"bfcl_irrelevance": 79.4,
|
|
2886
|
+
"composite": 0.37448559670781895,
|
|
2887
|
+
"composite_rank": 267
|
|
2888
|
+
},
|
|
2889
|
+
{
|
|
2890
|
+
"name": "gemini-1.5-flash-002",
|
|
2891
|
+
"norm": "gemini-1.5-flash-002",
|
|
2892
|
+
"bfcl_overall": null,
|
|
2893
|
+
"bfcl_multi_turn": null,
|
|
2894
|
+
"bfcl_irrelevance": null,
|
|
2895
|
+
"arena_rating": 1309.2081334363131,
|
|
2896
|
+
"arena_rank": 235,
|
|
2897
|
+
"composite": 0.3726541554959786,
|
|
2898
|
+
"composite_rank": 268
|
|
2899
|
+
},
|
|
2900
|
+
{
|
|
2901
|
+
"name": "grok-2-mini-2024-08-13",
|
|
2902
|
+
"norm": "grok-2-mini-2024-08-13",
|
|
2903
|
+
"bfcl_overall": null,
|
|
2904
|
+
"bfcl_multi_turn": null,
|
|
2905
|
+
"bfcl_irrelevance": null,
|
|
2906
|
+
"arena_rating": 1308.42297704231,
|
|
2907
|
+
"arena_rank": 236,
|
|
2908
|
+
"composite": 0.3699731903485255,
|
|
2909
|
+
"composite_rank": 269
|
|
2910
|
+
},
|
|
2911
|
+
{
|
|
2912
|
+
"name": "granite-4.1-8b",
|
|
2913
|
+
"norm": "granite-4.1-8b",
|
|
2914
|
+
"bfcl_overall": null,
|
|
2915
|
+
"bfcl_multi_turn": null,
|
|
2916
|
+
"bfcl_irrelevance": null,
|
|
2917
|
+
"arena_rating": 1307.2683416964385,
|
|
2918
|
+
"arena_rank": 237,
|
|
2919
|
+
"composite": 0.3672922252010724,
|
|
2920
|
+
"composite_rank": 270
|
|
2921
|
+
},
|
|
2922
|
+
{
|
|
2923
|
+
"name": "Ministral-8B-Instruct-2410 (FC)",
|
|
2924
|
+
"norm": "ministral-8b-instruct-2410",
|
|
2925
|
+
"bfcl_overall": 11.1,
|
|
2926
|
+
"bfcl_multi_turn": 0,
|
|
2927
|
+
"bfcl_irrelevance": 100,
|
|
2928
|
+
"composite": 0.3662551440329218,
|
|
2929
|
+
"composite_rank": 271
|
|
2930
|
+
},
|
|
2931
|
+
{
|
|
2932
|
+
"name": "deepseek-v2.5",
|
|
2933
|
+
"norm": "deepseek-v2.5",
|
|
2934
|
+
"bfcl_overall": null,
|
|
2935
|
+
"bfcl_multi_turn": null,
|
|
2936
|
+
"bfcl_irrelevance": null,
|
|
2937
|
+
"arena_rating": 1307.093368887914,
|
|
2938
|
+
"arena_rank": 238,
|
|
2939
|
+
"composite": 0.3646112600536193,
|
|
2940
|
+
"composite_rank": 272
|
|
2941
|
+
},
|
|
2942
|
+
{
|
|
2943
|
+
"name": "athene-70b-0725",
|
|
2944
|
+
"norm": "athene-70b-0725",
|
|
2945
|
+
"bfcl_overall": null,
|
|
2946
|
+
"bfcl_multi_turn": null,
|
|
2947
|
+
"bfcl_irrelevance": null,
|
|
2948
|
+
"arena_rating": 1306.3046422757807,
|
|
2949
|
+
"arena_rank": 239,
|
|
2950
|
+
"composite": 0.36193029490616624,
|
|
2951
|
+
"composite_rank": 273
|
|
2952
|
+
},
|
|
2953
|
+
{
|
|
2954
|
+
"name": "mercury",
|
|
2955
|
+
"norm": "mercury",
|
|
2956
|
+
"bfcl_overall": null,
|
|
2957
|
+
"bfcl_multi_turn": null,
|
|
2958
|
+
"bfcl_irrelevance": null,
|
|
2959
|
+
"arena_rating": 1306.0580726496096,
|
|
2960
|
+
"arena_rank": 240,
|
|
2961
|
+
"composite": 0.35924932975871315,
|
|
2962
|
+
"composite_rank": 274
|
|
2963
|
+
},
|
|
2964
|
+
{
|
|
2965
|
+
"name": "Llama-3.3-70B-Instruct (FC)",
|
|
2966
|
+
"norm": "llama-3.3-70b-instruct",
|
|
2967
|
+
"bfcl_overall": 31.9,
|
|
2968
|
+
"bfcl_multi_turn": 21.5,
|
|
2969
|
+
"bfcl_irrelevance": 53.53,
|
|
2970
|
+
"arena_rating": 1318.1597154752596,
|
|
2971
|
+
"arena_rank": 223,
|
|
2972
|
+
"composite": 0.35737927382252677,
|
|
2973
|
+
"composite_rank": 275
|
|
2974
|
+
},
|
|
2975
|
+
{
|
|
2976
|
+
"name": "olmo-3-32b-think",
|
|
2977
|
+
"norm": "olmo-3-32b-think",
|
|
2978
|
+
"bfcl_overall": null,
|
|
2979
|
+
"bfcl_multi_turn": null,
|
|
2980
|
+
"bfcl_irrelevance": null,
|
|
2981
|
+
"arena_rating": 1305.805251821463,
|
|
2982
|
+
"arena_rank": 241,
|
|
2983
|
+
"composite": 0.35656836461126007,
|
|
2984
|
+
"composite_rank": 276
|
|
2985
|
+
},
|
|
2986
|
+
{
|
|
2987
|
+
"name": "xLAM-2-1b-fc-r (FC)",
|
|
2988
|
+
"norm": "xlam-2-1b-fc-r",
|
|
2989
|
+
"bfcl_overall": 30.44,
|
|
2990
|
+
"bfcl_multi_turn": 36,
|
|
2991
|
+
"bfcl_irrelevance": 64.47,
|
|
2992
|
+
"composite": 0.35390946502057613,
|
|
2993
|
+
"composite_rank": 277
|
|
2994
|
+
},
|
|
2995
|
+
{
|
|
2996
|
+
"name": "magistral-medium-2506",
|
|
2997
|
+
"norm": "magistral-medium-2506",
|
|
2998
|
+
"bfcl_overall": null,
|
|
2999
|
+
"bfcl_multi_turn": null,
|
|
3000
|
+
"bfcl_irrelevance": null,
|
|
3001
|
+
"arena_rating": 1304.0556277437709,
|
|
3002
|
+
"arena_rank": 243,
|
|
3003
|
+
"composite": 0.3512064343163539,
|
|
3004
|
+
"composite_rank": 278
|
|
3005
|
+
},
|
|
3006
|
+
{
|
|
3007
|
+
"name": "Granite-3.2-8B-Instruct (FC)",
|
|
3008
|
+
"norm": "granite-3.2-8b-instruct",
|
|
3009
|
+
"bfcl_overall": 26.87,
|
|
3010
|
+
"bfcl_multi_turn": 7.38,
|
|
3011
|
+
"bfcl_irrelevance": 80.53,
|
|
3012
|
+
"composite": 0.34979423868312765,
|
|
3013
|
+
"composite_rank": 279
|
|
3014
|
+
},
|
|
3015
|
+
{
|
|
3016
|
+
"name": "mistral-small-3.1-24b-instruct-2503",
|
|
3017
|
+
"norm": "mistral-small-3.1-24b-instruct-2503",
|
|
3018
|
+
"bfcl_overall": null,
|
|
3019
|
+
"bfcl_multi_turn": null,
|
|
3020
|
+
"bfcl_irrelevance": null,
|
|
3021
|
+
"arena_rating": 1303.324636250603,
|
|
3022
|
+
"arena_rank": 244,
|
|
3023
|
+
"composite": 0.3485254691689008,
|
|
3024
|
+
"composite_rank": 280
|
|
3025
|
+
},
|
|
3026
|
+
{
|
|
3027
|
+
"name": "qwen2.5-72b-instruct",
|
|
3028
|
+
"norm": "qwen2.5-72b-instruct",
|
|
3029
|
+
"bfcl_overall": null,
|
|
3030
|
+
"bfcl_multi_turn": null,
|
|
3031
|
+
"bfcl_irrelevance": null,
|
|
3032
|
+
"arena_rating": 1302.8068731813075,
|
|
3033
|
+
"arena_rank": 246,
|
|
3034
|
+
"composite": 0.34316353887399464,
|
|
3035
|
+
"composite_rank": 281
|
|
3036
|
+
},
|
|
3037
|
+
{
|
|
3038
|
+
"name": "llama-3.1-nemotron-70b-instruct",
|
|
3039
|
+
"norm": "llama-3.1-nemotron-70b-instruct",
|
|
3040
|
+
"bfcl_overall": null,
|
|
3041
|
+
"bfcl_multi_turn": null,
|
|
3042
|
+
"bfcl_irrelevance": null,
|
|
3043
|
+
"arena_rating": 1298.958790412238,
|
|
3044
|
+
"arena_rank": 247,
|
|
3045
|
+
"composite": 0.34048257372654156,
|
|
3046
|
+
"composite_rank": 282
|
|
3047
|
+
},
|
|
3048
|
+
{
|
|
3049
|
+
"name": "hunyuan-large-vision",
|
|
3050
|
+
"norm": "hunyuan-large-vision",
|
|
3051
|
+
"bfcl_overall": null,
|
|
3052
|
+
"bfcl_multi_turn": null,
|
|
3053
|
+
"bfcl_irrelevance": null,
|
|
3054
|
+
"arena_rating": 1294.0115829587996,
|
|
3055
|
+
"arena_rank": 248,
|
|
3056
|
+
"composite": 0.3378016085790885,
|
|
3057
|
+
"composite_rank": 283
|
|
3058
|
+
},
|
|
3059
|
+
{
|
|
3060
|
+
"name": "llama-3.1-70b-instruct",
|
|
3061
|
+
"norm": "llama-3.1-70b-instruct",
|
|
3062
|
+
"bfcl_overall": null,
|
|
3063
|
+
"bfcl_multi_turn": null,
|
|
3064
|
+
"bfcl_irrelevance": null,
|
|
3065
|
+
"arena_rating": 1293.166824567864,
|
|
3066
|
+
"arena_rank": 249,
|
|
3067
|
+
"composite": 0.3351206434316354,
|
|
3068
|
+
"composite_rank": 284
|
|
3069
|
+
},
|
|
3070
|
+
{
|
|
3071
|
+
"name": "amazon-nova-pro-v1.0",
|
|
3072
|
+
"norm": "amazon-nova-pro-v1.0",
|
|
3073
|
+
"bfcl_overall": null,
|
|
3074
|
+
"bfcl_multi_turn": null,
|
|
3075
|
+
"bfcl_irrelevance": null,
|
|
3076
|
+
"arena_rating": 1290.0254853871184,
|
|
3077
|
+
"arena_rank": 250,
|
|
3078
|
+
"composite": 0.3324396782841823,
|
|
3079
|
+
"composite_rank": 285
|
|
3080
|
+
},
|
|
3081
|
+
{
|
|
3082
|
+
"name": "jamba-1.5-large",
|
|
3083
|
+
"norm": "jamba-1.5-large",
|
|
3084
|
+
"bfcl_overall": null,
|
|
3085
|
+
"bfcl_multi_turn": null,
|
|
3086
|
+
"bfcl_irrelevance": null,
|
|
3087
|
+
"arena_rating": 1289.0275844843366,
|
|
3088
|
+
"arena_rank": 251,
|
|
3089
|
+
"composite": 0.3297587131367292,
|
|
3090
|
+
"composite_rank": 286
|
|
3091
|
+
},
|
|
3092
|
+
{
|
|
3093
|
+
"name": "gemma-2-27b-it",
|
|
3094
|
+
"norm": "gemma-2-27b-it",
|
|
3095
|
+
"bfcl_overall": null,
|
|
3096
|
+
"bfcl_multi_turn": null,
|
|
3097
|
+
"bfcl_irrelevance": null,
|
|
3098
|
+
"arena_rating": 1288.8907150778873,
|
|
3099
|
+
"arena_rank": 252,
|
|
3100
|
+
"composite": 0.32707774798927614,
|
|
3101
|
+
"composite_rank": 287
|
|
3102
|
+
},
|
|
3103
|
+
{
|
|
3104
|
+
"name": "reka-core-20240904",
|
|
3105
|
+
"norm": "reka-core-20240904",
|
|
3106
|
+
"bfcl_overall": null,
|
|
3107
|
+
"bfcl_multi_turn": null,
|
|
3108
|
+
"bfcl_irrelevance": null,
|
|
3109
|
+
"arena_rating": 1287.7303637485643,
|
|
3110
|
+
"arena_rank": 253,
|
|
3111
|
+
"composite": 0.32439678284182305,
|
|
3112
|
+
"composite_rank": 288
|
|
3113
|
+
},
|
|
3114
|
+
{
|
|
3115
|
+
"name": "ibm-granite-h-small",
|
|
3116
|
+
"norm": "ibm-granite-h-small",
|
|
3117
|
+
"bfcl_overall": null,
|
|
3118
|
+
"bfcl_multi_turn": null,
|
|
3119
|
+
"bfcl_irrelevance": null,
|
|
3120
|
+
"arena_rating": 1286.960433619754,
|
|
3121
|
+
"arena_rank": 254,
|
|
3122
|
+
"composite": 0.32171581769436997,
|
|
3123
|
+
"composite_rank": 289
|
|
3124
|
+
},
|
|
3125
|
+
{
|
|
3126
|
+
"name": "gpt-4-0314",
|
|
3127
|
+
"norm": "gpt-4-0314",
|
|
3128
|
+
"bfcl_overall": null,
|
|
3129
|
+
"bfcl_multi_turn": null,
|
|
3130
|
+
"bfcl_irrelevance": null,
|
|
3131
|
+
"arena_rating": 1286.6940746850623,
|
|
3132
|
+
"arena_rank": 255,
|
|
3133
|
+
"composite": 0.3190348525469169,
|
|
3134
|
+
"composite_rank": 290
|
|
3135
|
+
},
|
|
3136
|
+
{
|
|
3137
|
+
"name": "Granite-3.1-8B-Instruct (FC)",
|
|
3138
|
+
"norm": "granite-3.1-8b-instruct",
|
|
3139
|
+
"bfcl_overall": 27.1,
|
|
3140
|
+
"bfcl_multi_turn": 7.5,
|
|
3141
|
+
"bfcl_irrelevance": 79.98,
|
|
3142
|
+
"arena_rating": 1207.806784538892,
|
|
3143
|
+
"arena_rank": 302,
|
|
3144
|
+
"composite": 0.316775891172674,
|
|
3145
|
+
"composite_rank": 291
|
|
3146
|
+
},
|
|
3147
|
+
{
|
|
3148
|
+
"name": "gemini-1.5-flash-001",
|
|
3149
|
+
"norm": "gemini-1.5-flash-001",
|
|
3150
|
+
"bfcl_overall": null,
|
|
3151
|
+
"bfcl_multi_turn": null,
|
|
3152
|
+
"bfcl_irrelevance": null,
|
|
3153
|
+
"arena_rating": 1286.154556730809,
|
|
3154
|
+
"arena_rank": 256,
|
|
3155
|
+
"composite": 0.3163538873994638,
|
|
3156
|
+
"composite_rank": 292
|
|
3157
|
+
},
|
|
3158
|
+
{
|
|
3159
|
+
"name": "llama-3.1-tulu-3-70b",
|
|
3160
|
+
"norm": "llama-3.1-tulu-3-70b",
|
|
3161
|
+
"bfcl_overall": null,
|
|
3162
|
+
"bfcl_multi_turn": null,
|
|
3163
|
+
"bfcl_irrelevance": null,
|
|
3164
|
+
"arena_rating": 1285.9427029679634,
|
|
3165
|
+
"arena_rank": 257,
|
|
3166
|
+
"composite": 0.3136729222520107,
|
|
3167
|
+
"composite_rank": 293
|
|
3168
|
+
},
|
|
3169
|
+
{
|
|
3170
|
+
"name": "RZN-T (Prompt)",
|
|
3171
|
+
"norm": "rzn-t",
|
|
3172
|
+
"bfcl_overall": 22.25,
|
|
3173
|
+
"bfcl_multi_turn": 2.88,
|
|
3174
|
+
"bfcl_irrelevance": 82.41,
|
|
3175
|
+
"composite": 0.3127572016460905,
|
|
3176
|
+
"composite_rank": 294
|
|
3177
|
+
},
|
|
3178
|
+
{
|
|
3179
|
+
"name": "llama-3.1-nemotron-51b-instruct",
|
|
3180
|
+
"norm": "llama-3.1-nemotron-51b-instruct",
|
|
3181
|
+
"bfcl_overall": null,
|
|
3182
|
+
"bfcl_multi_turn": null,
|
|
3183
|
+
"bfcl_irrelevance": null,
|
|
3184
|
+
"arena_rating": 1285.9081920438484,
|
|
3185
|
+
"arena_rank": 258,
|
|
3186
|
+
"composite": 0.3109919571045576,
|
|
3187
|
+
"composite_rank": 295
|
|
3188
|
+
},
|
|
3189
|
+
{
|
|
3190
|
+
"name": "Qwen3-0.6B (FC)",
|
|
3191
|
+
"norm": "qwen3-0.6b",
|
|
3192
|
+
"bfcl_overall": 23.93,
|
|
3193
|
+
"bfcl_multi_turn": 3.62,
|
|
3194
|
+
"bfcl_irrelevance": 80.84,
|
|
3195
|
+
"composite": 0.308641975308642,
|
|
3196
|
+
"composite_rank": 296
|
|
3197
|
+
},
|
|
3198
|
+
{
|
|
3199
|
+
"name": "Falcon3-1B-Instruct (FC)",
|
|
3200
|
+
"norm": "falcon3-1b-instruct",
|
|
3201
|
+
"bfcl_overall": 11.08,
|
|
3202
|
+
"bfcl_multi_turn": 0,
|
|
3203
|
+
"bfcl_irrelevance": 87.3,
|
|
3204
|
+
"composite": 0.308641975308642,
|
|
3205
|
+
"composite_rank": 297
|
|
3206
|
+
},
|
|
3207
|
+
{
|
|
3208
|
+
"name": "olmo-3.1-32b-think",
|
|
3209
|
+
"norm": "olmo-3.1-32b-think",
|
|
3210
|
+
"bfcl_overall": null,
|
|
3211
|
+
"bfcl_multi_turn": null,
|
|
3212
|
+
"bfcl_irrelevance": null,
|
|
3213
|
+
"arena_rating": 1284.9348499227328,
|
|
3214
|
+
"arena_rank": 259,
|
|
3215
|
+
"composite": 0.30831099195710454,
|
|
3216
|
+
"composite_rank": 298
|
|
3217
|
+
},
|
|
3218
|
+
{
|
|
3219
|
+
"name": "claude-3-sonnet-20240229",
|
|
3220
|
+
"norm": "claude-3-sonnet-20240229",
|
|
3221
|
+
"bfcl_overall": null,
|
|
3222
|
+
"bfcl_multi_turn": null,
|
|
3223
|
+
"bfcl_irrelevance": null,
|
|
3224
|
+
"arena_rating": 1280.5316585640678,
|
|
3225
|
+
"arena_rank": 260,
|
|
3226
|
+
"composite": 0.30563002680965146,
|
|
3227
|
+
"composite_rank": 299
|
|
3228
|
+
},
|
|
3229
|
+
{
|
|
3230
|
+
"name": "gemma-2-9b-it-simpo",
|
|
3231
|
+
"norm": "gemma-2-9b-it-simpo",
|
|
3232
|
+
"bfcl_overall": null,
|
|
3233
|
+
"bfcl_multi_turn": null,
|
|
3234
|
+
"bfcl_irrelevance": null,
|
|
3235
|
+
"arena_rating": 1279.8787287717628,
|
|
3236
|
+
"arena_rank": 261,
|
|
3237
|
+
"composite": 0.30294906166219837,
|
|
3238
|
+
"composite_rank": 300
|
|
3239
|
+
},
|
|
3240
|
+
{
|
|
3241
|
+
"name": "Llama-4-Scout-17B-16E-Instruct (FC)",
|
|
3242
|
+
"norm": "llama-4-scout-17b-16e-instruct",
|
|
3243
|
+
"bfcl_overall": 28.13,
|
|
3244
|
+
"bfcl_multi_turn": 9,
|
|
3245
|
+
"bfcl_irrelevance": 44.92,
|
|
3246
|
+
"arena_rating": 1322.771548333306,
|
|
3247
|
+
"arena_rank": 217,
|
|
3248
|
+
"composite": 0.3027587462350644,
|
|
3249
|
+
"composite_rank": 301
|
|
3250
|
+
},
|
|
3251
|
+
{
|
|
3252
|
+
"name": "nemotron-4-340b-instruct",
|
|
3253
|
+
"norm": "nemotron-4-340b-instruct",
|
|
3254
|
+
"bfcl_overall": null,
|
|
3255
|
+
"bfcl_multi_turn": null,
|
|
3256
|
+
"bfcl_irrelevance": null,
|
|
3257
|
+
"arena_rating": 1276.5167807101316,
|
|
3258
|
+
"arena_rank": 262,
|
|
3259
|
+
"composite": 0.3002680965147453,
|
|
3260
|
+
"composite_rank": 302
|
|
3261
|
+
},
|
|
3262
|
+
{
|
|
3263
|
+
"name": "llama-3-70b-instruct",
|
|
3264
|
+
"norm": "llama-3-70b-instruct",
|
|
3265
|
+
"bfcl_overall": null,
|
|
3266
|
+
"bfcl_multi_turn": null,
|
|
3267
|
+
"bfcl_irrelevance": null,
|
|
3268
|
+
"arena_rating": 1275.9216304218548,
|
|
3269
|
+
"arena_rank": 263,
|
|
3270
|
+
"composite": 0.2975871313672922,
|
|
3271
|
+
"composite_rank": 303
|
|
3272
|
+
},
|
|
3273
|
+
{
|
|
3274
|
+
"name": "command-r-plus-08-2024",
|
|
3275
|
+
"norm": "command-r-plus-08-2024",
|
|
3276
|
+
"bfcl_overall": null,
|
|
3277
|
+
"bfcl_multi_turn": null,
|
|
3278
|
+
"bfcl_irrelevance": null,
|
|
3279
|
+
"arena_rating": 1275.8022822191342,
|
|
3280
|
+
"arena_rank": 264,
|
|
3281
|
+
"composite": 0.2949061662198391,
|
|
3282
|
+
"composite_rank": 304
|
|
3283
|
+
},
|
|
3284
|
+
{
|
|
3285
|
+
"name": "gpt-4-0613",
|
|
3286
|
+
"norm": "gpt-4-0613",
|
|
3287
|
+
"bfcl_overall": null,
|
|
3288
|
+
"bfcl_multi_turn": null,
|
|
3289
|
+
"bfcl_irrelevance": null,
|
|
3290
|
+
"arena_rating": 1274.9511817914433,
|
|
3291
|
+
"arena_rank": 265,
|
|
3292
|
+
"composite": 0.29222520107238603,
|
|
3293
|
+
"composite_rank": 305
|
|
3294
|
+
},
|
|
3295
|
+
{
|
|
3296
|
+
"name": "mistral-small-24b-instruct-2501",
|
|
3297
|
+
"norm": "mistral-small-24b-instruct-2501",
|
|
3298
|
+
"bfcl_overall": null,
|
|
3299
|
+
"bfcl_multi_turn": null,
|
|
3300
|
+
"bfcl_irrelevance": null,
|
|
3301
|
+
"arena_rating": 1274.0894490605897,
|
|
3302
|
+
"arena_rank": 266,
|
|
3303
|
+
"composite": 0.28954423592493295,
|
|
3304
|
+
"composite_rank": 306
|
|
3305
|
+
},
|
|
3306
|
+
{
|
|
3307
|
+
"name": "glm-4-0520",
|
|
3308
|
+
"norm": "glm-4-0520",
|
|
3309
|
+
"bfcl_overall": null,
|
|
3310
|
+
"bfcl_multi_turn": null,
|
|
3311
|
+
"bfcl_irrelevance": null,
|
|
3312
|
+
"arena_rating": 1272.958162686396,
|
|
3313
|
+
"arena_rank": 267,
|
|
3314
|
+
"composite": 0.28686327077747986,
|
|
3315
|
+
"composite_rank": 307
|
|
3316
|
+
},
|
|
3317
|
+
{
|
|
3318
|
+
"name": "reka-flash-20240904",
|
|
3319
|
+
"norm": "reka-flash-20240904",
|
|
3320
|
+
"bfcl_overall": null,
|
|
3321
|
+
"bfcl_multi_turn": null,
|
|
3322
|
+
"bfcl_irrelevance": null,
|
|
3323
|
+
"arena_rating": 1271.7809566686817,
|
|
3324
|
+
"arena_rank": 268,
|
|
3325
|
+
"composite": 0.2841823056300268,
|
|
3326
|
+
"composite_rank": 308
|
|
3327
|
+
},
|
|
3328
|
+
{
|
|
3329
|
+
"name": "qwen2.5-coder-32b-instruct",
|
|
3330
|
+
"norm": "qwen2.5-coder-32b-instruct",
|
|
3331
|
+
"bfcl_overall": null,
|
|
3332
|
+
"bfcl_multi_turn": null,
|
|
3333
|
+
"bfcl_irrelevance": null,
|
|
3334
|
+
"arena_rating": 1270.3716190569676,
|
|
3335
|
+
"arena_rank": 269,
|
|
3336
|
+
"composite": 0.2815013404825737,
|
|
3337
|
+
"composite_rank": 309
|
|
3338
|
+
},
|
|
3339
|
+
{
|
|
3340
|
+
"name": "c4ai-aya-expanse-32b",
|
|
3341
|
+
"norm": "c4ai-aya-expanse-32b",
|
|
3342
|
+
"bfcl_overall": null,
|
|
3343
|
+
"bfcl_multi_turn": null,
|
|
3344
|
+
"bfcl_irrelevance": null,
|
|
3345
|
+
"arena_rating": 1266.8851138121215,
|
|
3346
|
+
"arena_rank": 270,
|
|
3347
|
+
"composite": 0.2788203753351206,
|
|
3348
|
+
"composite_rank": 310
|
|
3349
|
+
},
|
|
3350
|
+
{
|
|
3351
|
+
"name": "gemma-2-9b-it",
|
|
3352
|
+
"norm": "gemma-2-9b-it",
|
|
3353
|
+
"bfcl_overall": null,
|
|
3354
|
+
"bfcl_multi_turn": null,
|
|
3355
|
+
"bfcl_irrelevance": null,
|
|
3356
|
+
"arena_rating": 1266.4040419666183,
|
|
3357
|
+
"arena_rank": 271,
|
|
3358
|
+
"composite": 0.2761394101876675,
|
|
3359
|
+
"composite_rank": 311
|
|
3360
|
+
},
|
|
3361
|
+
{
|
|
3362
|
+
"name": "deepseek-coder-v2",
|
|
3363
|
+
"norm": "deepseek-coder-v2",
|
|
3364
|
+
"bfcl_overall": null,
|
|
3365
|
+
"bfcl_multi_turn": null,
|
|
3366
|
+
"bfcl_irrelevance": null,
|
|
3367
|
+
"arena_rating": 1264.4941998871852,
|
|
3368
|
+
"arena_rank": 272,
|
|
3369
|
+
"composite": 0.27345844504021444,
|
|
3370
|
+
"composite_rank": 312
|
|
3371
|
+
},
|
|
3372
|
+
{
|
|
3373
|
+
"name": "qwen2-72b-instruct",
|
|
3374
|
+
"norm": "qwen2-72b-instruct",
|
|
3375
|
+
"bfcl_overall": null,
|
|
3376
|
+
"bfcl_multi_turn": null,
|
|
3377
|
+
"bfcl_irrelevance": null,
|
|
3378
|
+
"arena_rating": 1261.1114676759182,
|
|
3379
|
+
"arena_rank": 273,
|
|
3380
|
+
"composite": 0.27077747989276135,
|
|
3381
|
+
"composite_rank": 313
|
|
3382
|
+
},
|
|
3383
|
+
{
|
|
3384
|
+
"name": "command-r-plus",
|
|
3385
|
+
"norm": "command-r-plus",
|
|
3386
|
+
"bfcl_overall": null,
|
|
3387
|
+
"bfcl_multi_turn": null,
|
|
3388
|
+
"bfcl_irrelevance": null,
|
|
3389
|
+
"arena_rating": 1261.0612938024244,
|
|
3390
|
+
"arena_rank": 274,
|
|
3391
|
+
"composite": 0.26809651474530827,
|
|
3392
|
+
"composite_rank": 314
|
|
3393
|
+
},
|
|
3394
|
+
{
|
|
3395
|
+
"name": "claude-3-haiku-20240307",
|
|
3396
|
+
"norm": "claude-3-haiku-20240307",
|
|
3397
|
+
"bfcl_overall": null,
|
|
3398
|
+
"bfcl_multi_turn": null,
|
|
3399
|
+
"bfcl_irrelevance": null,
|
|
3400
|
+
"arena_rating": 1260.7963110356277,
|
|
3401
|
+
"arena_rank": 275,
|
|
3402
|
+
"composite": 0.2654155495978552,
|
|
3403
|
+
"composite_rank": 315
|
|
3404
|
+
},
|
|
3405
|
+
{
|
|
3406
|
+
"name": "amazon-nova-lite-v1.0",
|
|
3407
|
+
"norm": "amazon-nova-lite-v1.0",
|
|
3408
|
+
"bfcl_overall": null,
|
|
3409
|
+
"bfcl_multi_turn": null,
|
|
3410
|
+
"bfcl_irrelevance": null,
|
|
3411
|
+
"arena_rating": 1260.3437628861898,
|
|
3412
|
+
"arena_rank": 276,
|
|
3413
|
+
"composite": 0.2627345844504021,
|
|
3414
|
+
"composite_rank": 316
|
|
3415
|
+
},
|
|
3416
|
+
{
|
|
3417
|
+
"name": "gemini-1.5-flash-8b-001",
|
|
3418
|
+
"norm": "gemini-1.5-flash-8b-001",
|
|
3419
|
+
"bfcl_overall": null,
|
|
3420
|
+
"bfcl_multi_turn": null,
|
|
3421
|
+
"bfcl_irrelevance": null,
|
|
3422
|
+
"arena_rating": 1258.579756976915,
|
|
3423
|
+
"arena_rank": 277,
|
|
3424
|
+
"composite": 0.260053619302949,
|
|
3425
|
+
"composite_rank": 317
|
|
3426
|
+
},
|
|
3427
|
+
{
|
|
3428
|
+
"name": "Open-Mistral-Nemo-2407 (FC)",
|
|
3429
|
+
"norm": "open-mistral-nemo-2407",
|
|
3430
|
+
"bfcl_overall": 27.63,
|
|
3431
|
+
"bfcl_multi_turn": 7.75,
|
|
3432
|
+
"bfcl_irrelevance": 61.77,
|
|
3433
|
+
"composite": 0.2592592592592593,
|
|
3434
|
+
"composite_rank": 318
|
|
3435
|
+
},
|
|
3436
|
+
{
|
|
3437
|
+
"name": "olmo-2-0325-32b-instruct",
|
|
3438
|
+
"norm": "olmo-2-0325-32b-instruct",
|
|
3439
|
+
"bfcl_overall": null,
|
|
3440
|
+
"bfcl_multi_turn": null,
|
|
3441
|
+
"bfcl_irrelevance": null,
|
|
3442
|
+
"arena_rating": 1251.350734020075,
|
|
3443
|
+
"arena_rank": 279,
|
|
3444
|
+
"composite": 0.25469168900804284,
|
|
3445
|
+
"composite_rank": 319
|
|
3446
|
+
},
|
|
3447
|
+
{
|
|
3448
|
+
"name": "command-r-08-2024",
|
|
3449
|
+
"norm": "command-r-08-2024",
|
|
3450
|
+
"bfcl_overall": null,
|
|
3451
|
+
"bfcl_multi_turn": null,
|
|
3452
|
+
"bfcl_irrelevance": null,
|
|
3453
|
+
"arena_rating": 1249.6537667524062,
|
|
3454
|
+
"arena_rank": 280,
|
|
3455
|
+
"composite": 0.25201072386058976,
|
|
3456
|
+
"composite_rank": 320
|
|
3457
|
+
},
|
|
3458
|
+
{
|
|
3459
|
+
"name": "mistral-large-2402",
|
|
3460
|
+
"norm": "mistral-large-2402",
|
|
3461
|
+
"bfcl_overall": null,
|
|
3462
|
+
"bfcl_multi_turn": null,
|
|
3463
|
+
"bfcl_irrelevance": null,
|
|
3464
|
+
"arena_rating": 1241.6855835233423,
|
|
3465
|
+
"arena_rank": 281,
|
|
3466
|
+
"composite": 0.24932975871313678,
|
|
3467
|
+
"composite_rank": 321
|
|
3468
|
+
},
|
|
3469
|
+
{
|
|
3470
|
+
"name": "Hammer2.1-0.5b (FC)",
|
|
3471
|
+
"norm": "hammer2.1-0.5b",
|
|
3472
|
+
"bfcl_overall": 21.22,
|
|
3473
|
+
"bfcl_multi_turn": 2.88,
|
|
3474
|
+
"bfcl_irrelevance": 80.79,
|
|
3475
|
+
"composite": 0.24691358024691357,
|
|
3476
|
+
"composite_rank": 322
|
|
3477
|
+
},
|
|
3478
|
+
{
|
|
3479
|
+
"name": "amazon-nova-micro-v1.0",
|
|
3480
|
+
"norm": "amazon-nova-micro-v1.0",
|
|
3481
|
+
"bfcl_overall": null,
|
|
3482
|
+
"bfcl_multi_turn": null,
|
|
3483
|
+
"bfcl_irrelevance": null,
|
|
3484
|
+
"arena_rating": 1240.594150754738,
|
|
3485
|
+
"arena_rank": 282,
|
|
3486
|
+
"composite": 0.2466487935656837,
|
|
3487
|
+
"composite_rank": 323
|
|
3488
|
+
},
|
|
3489
|
+
{
|
|
3490
|
+
"name": "jamba-1.5-mini",
|
|
3491
|
+
"norm": "jamba-1.5-mini",
|
|
3492
|
+
"bfcl_overall": null,
|
|
3493
|
+
"bfcl_multi_turn": null,
|
|
3494
|
+
"bfcl_irrelevance": null,
|
|
3495
|
+
"arena_rating": 1239.3247050891675,
|
|
3496
|
+
"arena_rank": 283,
|
|
3497
|
+
"composite": 0.24396782841823061,
|
|
3498
|
+
"composite_rank": 324
|
|
3499
|
+
},
|
|
3500
|
+
{
|
|
3501
|
+
"name": "MiniCPM3-4B-FC (FC)",
|
|
3502
|
+
"norm": "minicpm3-4b-fc",
|
|
3503
|
+
"bfcl_overall": 25.55,
|
|
3504
|
+
"bfcl_multi_turn": 3.88,
|
|
3505
|
+
"bfcl_irrelevance": 72.84,
|
|
3506
|
+
"composite": 0.24279835390946503,
|
|
3507
|
+
"composite_rank": 325
|
|
3508
|
+
},
|
|
3509
|
+
{
|
|
3510
|
+
"name": "Granite-20b-FunctionCalling (FC)",
|
|
3511
|
+
"norm": "granite-20b-functioncalling",
|
|
3512
|
+
"bfcl_overall": 23.23,
|
|
3513
|
+
"bfcl_multi_turn": 5.38,
|
|
3514
|
+
"bfcl_irrelevance": 75.13,
|
|
3515
|
+
"composite": 0.24279835390946503,
|
|
3516
|
+
"composite_rank": 326
|
|
3517
|
+
},
|
|
3518
|
+
{
|
|
3519
|
+
"name": "ministral-8b-2410",
|
|
3520
|
+
"norm": "ministral-8b-2410",
|
|
3521
|
+
"bfcl_overall": null,
|
|
3522
|
+
"bfcl_multi_turn": null,
|
|
3523
|
+
"bfcl_irrelevance": null,
|
|
3524
|
+
"arena_rating": 1237.2775343704943,
|
|
3525
|
+
"arena_rank": 284,
|
|
3526
|
+
"composite": 0.24128686327077753,
|
|
3527
|
+
"composite_rank": 327
|
|
3528
|
+
},
|
|
3529
|
+
{
|
|
3530
|
+
"name": "gemini-pro-dev-api",
|
|
3531
|
+
"norm": "gemini-pro-dev-api",
|
|
3532
|
+
"bfcl_overall": null,
|
|
3533
|
+
"bfcl_multi_turn": null,
|
|
3534
|
+
"bfcl_irrelevance": null,
|
|
3535
|
+
"arena_rating": 1235.6826773289806,
|
|
3536
|
+
"arena_rank": 285,
|
|
3537
|
+
"composite": 0.23860589812332444,
|
|
3538
|
+
"composite_rank": 328
|
|
3539
|
+
},
|
|
3540
|
+
{
|
|
3541
|
+
"name": "qwen1.5-110b-chat",
|
|
3542
|
+
"norm": "qwen1.5-110b-chat",
|
|
3543
|
+
"bfcl_overall": null,
|
|
3544
|
+
"bfcl_multi_turn": null,
|
|
3545
|
+
"bfcl_irrelevance": null,
|
|
3546
|
+
"arena_rating": 1233.4729195527507,
|
|
3547
|
+
"arena_rank": 286,
|
|
3548
|
+
"composite": 0.23592493297587136,
|
|
3549
|
+
"composite_rank": 329
|
|
3550
|
+
},
|
|
3551
|
+
{
|
|
3552
|
+
"name": "hunyuan-standard-256k",
|
|
3553
|
+
"norm": "hunyuan-standard-256k",
|
|
3554
|
+
"bfcl_overall": null,
|
|
3555
|
+
"bfcl_multi_turn": null,
|
|
3556
|
+
"bfcl_irrelevance": null,
|
|
3557
|
+
"arena_rating": 1233.228747147293,
|
|
3558
|
+
"arena_rank": 287,
|
|
3559
|
+
"composite": 0.23324396782841827,
|
|
3560
|
+
"composite_rank": 330
|
|
3561
|
+
},
|
|
3562
|
+
{
|
|
3563
|
+
"name": "reka-flash-21b-20240226-online",
|
|
3564
|
+
"norm": "reka-flash-21b-20240226-online",
|
|
3565
|
+
"bfcl_overall": null,
|
|
3566
|
+
"bfcl_multi_turn": null,
|
|
3567
|
+
"bfcl_irrelevance": null,
|
|
3568
|
+
"arena_rating": 1232.7572410684552,
|
|
3569
|
+
"arena_rank": 288,
|
|
3570
|
+
"composite": 0.2305630026809652,
|
|
3571
|
+
"composite_rank": 331
|
|
3572
|
+
},
|
|
3573
|
+
{
|
|
3574
|
+
"name": "qwen1.5-72b-chat",
|
|
3575
|
+
"norm": "qwen1.5-72b-chat",
|
|
3576
|
+
"bfcl_overall": null,
|
|
3577
|
+
"bfcl_multi_turn": null,
|
|
3578
|
+
"bfcl_irrelevance": null,
|
|
3579
|
+
"arena_rating": 1232.6689338560461,
|
|
3580
|
+
"arena_rank": 289,
|
|
3581
|
+
"composite": 0.2278820375335121,
|
|
3582
|
+
"composite_rank": 332
|
|
3583
|
+
},
|
|
3584
|
+
{
|
|
3585
|
+
"name": "mixtral-8x22b-instruct-v0.1",
|
|
3586
|
+
"norm": "mixtral-8x22b-instruct-v0.1",
|
|
3587
|
+
"bfcl_overall": null,
|
|
3588
|
+
"bfcl_multi_turn": null,
|
|
3589
|
+
"bfcl_irrelevance": null,
|
|
3590
|
+
"arena_rating": 1228.703235886949,
|
|
3591
|
+
"arena_rank": 290,
|
|
3592
|
+
"composite": 0.22520107238605902,
|
|
3593
|
+
"composite_rank": 333
|
|
3594
|
+
},
|
|
3595
|
+
{
|
|
3596
|
+
"name": "command-r",
|
|
3597
|
+
"norm": "command-r",
|
|
3598
|
+
"bfcl_overall": null,
|
|
3599
|
+
"bfcl_multi_turn": null,
|
|
3600
|
+
"bfcl_irrelevance": null,
|
|
3601
|
+
"arena_rating": 1226.0541499225417,
|
|
3602
|
+
"arena_rank": 291,
|
|
3603
|
+
"composite": 0.22252010723860594,
|
|
3604
|
+
"composite_rank": 334
|
|
3605
|
+
},
|
|
3606
|
+
{
|
|
3607
|
+
"name": "Amazon-Nova-Pro-v1:0 (FC)",
|
|
3608
|
+
"norm": "amazon-nova-pro-v1:0",
|
|
3609
|
+
"bfcl_overall": 24.97,
|
|
3610
|
+
"bfcl_multi_turn": 1.88,
|
|
3611
|
+
"bfcl_irrelevance": 70.06,
|
|
3612
|
+
"composite": 0.22222222222222224,
|
|
3613
|
+
"composite_rank": 335
|
|
3614
|
+
},
|
|
3615
|
+
{
|
|
3616
|
+
"name": "reka-flash-21b-20240226",
|
|
3617
|
+
"norm": "reka-flash-21b-20240226",
|
|
3618
|
+
"bfcl_overall": null,
|
|
3619
|
+
"bfcl_multi_turn": null,
|
|
3620
|
+
"bfcl_irrelevance": null,
|
|
3621
|
+
"arena_rating": 1226.0414050489514,
|
|
3622
|
+
"arena_rank": 292,
|
|
3623
|
+
"composite": 0.21983914209115285,
|
|
3624
|
+
"composite_rank": 336
|
|
3625
|
+
},
|
|
3626
|
+
{
|
|
3627
|
+
"name": "gpt-3.5-turbo-0125",
|
|
3628
|
+
"norm": "gpt-3.5-turbo-0125",
|
|
3629
|
+
"bfcl_overall": null,
|
|
3630
|
+
"bfcl_multi_turn": null,
|
|
3631
|
+
"bfcl_irrelevance": null,
|
|
3632
|
+
"arena_rating": 1224.1573573860164,
|
|
3633
|
+
"arena_rank": 293,
|
|
3634
|
+
"composite": 0.21715817694369977,
|
|
3635
|
+
"composite_rank": 337
|
|
3636
|
+
},
|
|
3637
|
+
{
|
|
3638
|
+
"name": "llama-3-8b-instruct",
|
|
3639
|
+
"norm": "llama-3-8b-instruct",
|
|
3640
|
+
"bfcl_overall": null,
|
|
3641
|
+
"bfcl_multi_turn": null,
|
|
3642
|
+
"bfcl_irrelevance": null,
|
|
3643
|
+
"arena_rating": 1222.962099076614,
|
|
3644
|
+
"arena_rank": 294,
|
|
3645
|
+
"composite": 0.21447721179624668,
|
|
3646
|
+
"composite_rank": 338
|
|
3647
|
+
},
|
|
3648
|
+
{
|
|
3649
|
+
"name": "c4ai-aya-expanse-8b",
|
|
3650
|
+
"norm": "c4ai-aya-expanse-8b",
|
|
3651
|
+
"bfcl_overall": null,
|
|
3652
|
+
"bfcl_multi_turn": null,
|
|
3653
|
+
"bfcl_irrelevance": null,
|
|
3654
|
+
"arena_rating": 1222.8195751849842,
|
|
3655
|
+
"arena_rank": 295,
|
|
3656
|
+
"composite": 0.2117962466487936,
|
|
3657
|
+
"composite_rank": 339
|
|
3658
|
+
},
|
|
3659
|
+
{
|
|
3660
|
+
"name": "gemini-pro",
|
|
3661
|
+
"norm": "gemini-pro",
|
|
3662
|
+
"bfcl_overall": null,
|
|
3663
|
+
"bfcl_multi_turn": null,
|
|
3664
|
+
"bfcl_irrelevance": null,
|
|
3665
|
+
"arena_rating": 1222.3746074890967,
|
|
3666
|
+
"arena_rank": 296,
|
|
3667
|
+
"composite": 0.2091152815013405,
|
|
3668
|
+
"composite_rank": 340
|
|
3669
|
+
},
|
|
3670
|
+
{
|
|
3671
|
+
"name": "mistral-medium",
|
|
3672
|
+
"norm": "mistral-medium",
|
|
3673
|
+
"bfcl_overall": null,
|
|
3674
|
+
"bfcl_multi_turn": null,
|
|
3675
|
+
"bfcl_irrelevance": null,
|
|
3676
|
+
"arena_rating": 1221.9868851778324,
|
|
3677
|
+
"arena_rank": 297,
|
|
3678
|
+
"composite": 0.20643431635388743,
|
|
3679
|
+
"composite_rank": 341
|
|
3680
|
+
},
|
|
3681
|
+
{
|
|
3682
|
+
"name": "llama-3.1-tulu-3-8b",
|
|
3683
|
+
"norm": "llama-3.1-tulu-3-8b",
|
|
3684
|
+
"bfcl_overall": null,
|
|
3685
|
+
"bfcl_multi_turn": null,
|
|
3686
|
+
"bfcl_irrelevance": null,
|
|
3687
|
+
"arena_rating": 1220.4361629512687,
|
|
3688
|
+
"arena_rank": 298,
|
|
3689
|
+
"composite": 0.20375335120643434,
|
|
3690
|
+
"composite_rank": 342
|
|
3691
|
+
},
|
|
3692
|
+
{
|
|
3693
|
+
"name": "yi-1.5-34b-chat",
|
|
3694
|
+
"norm": "yi-1.5-34b-chat",
|
|
3695
|
+
"bfcl_overall": null,
|
|
3696
|
+
"bfcl_multi_turn": null,
|
|
3697
|
+
"bfcl_irrelevance": null,
|
|
3698
|
+
"arena_rating": 1212.4974936507806,
|
|
3699
|
+
"arena_rank": 299,
|
|
3700
|
+
"composite": 0.20107238605898126,
|
|
3701
|
+
"composite_rank": 343
|
|
3702
|
+
},
|
|
3703
|
+
{
|
|
3704
|
+
"name": "zephyr-orpo-141b-a35b-v0.1",
|
|
3705
|
+
"norm": "zephyr-orpo-141b-a35b-v0.1",
|
|
3706
|
+
"bfcl_overall": null,
|
|
3707
|
+
"bfcl_multi_turn": null,
|
|
3708
|
+
"bfcl_irrelevance": null,
|
|
3709
|
+
"arena_rating": 1212.1247077196801,
|
|
3710
|
+
"arena_rank": 300,
|
|
3711
|
+
"composite": 0.19839142091152817,
|
|
3712
|
+
"composite_rank": 344
|
|
3713
|
+
},
|
|
3714
|
+
{
|
|
3715
|
+
"name": "Amazon-Nova-Micro-v1:0 (FC)",
|
|
3716
|
+
"norm": "amazon-nova-micro-v1:0",
|
|
3717
|
+
"bfcl_overall": 22.29,
|
|
3718
|
+
"bfcl_multi_turn": 1.38,
|
|
3719
|
+
"bfcl_irrelevance": 70.65,
|
|
3720
|
+
"composite": 0.19753086419753088,
|
|
3721
|
+
"composite_rank": 345
|
|
3722
|
+
},
|
|
3723
|
+
{
|
|
3724
|
+
"name": "MiniCPM3-4B (Prompt)",
|
|
3725
|
+
"norm": "minicpm3-4b",
|
|
3726
|
+
"bfcl_overall": 22.08,
|
|
3727
|
+
"bfcl_multi_turn": 3.5,
|
|
3728
|
+
"bfcl_irrelevance": 73.71,
|
|
3729
|
+
"composite": 0.19341563786008234,
|
|
3730
|
+
"composite_rank": 346
|
|
3731
|
+
},
|
|
3732
|
+
{
|
|
3733
|
+
"name": "qwen1.5-32b-chat",
|
|
3734
|
+
"norm": "qwen1.5-32b-chat",
|
|
3735
|
+
"bfcl_overall": null,
|
|
3736
|
+
"bfcl_multi_turn": null,
|
|
3737
|
+
"bfcl_irrelevance": null,
|
|
3738
|
+
"arena_rating": 1203.1349042099632,
|
|
3739
|
+
"arena_rank": 303,
|
|
3740
|
+
"composite": 0.19034852546916892,
|
|
3741
|
+
"composite_rank": 347
|
|
3742
|
+
},
|
|
3743
|
+
{
|
|
3744
|
+
"name": "gpt-3.5-turbo-1106",
|
|
3745
|
+
"norm": "gpt-3.5-turbo-1106",
|
|
3746
|
+
"bfcl_overall": null,
|
|
3747
|
+
"bfcl_multi_turn": null,
|
|
3748
|
+
"bfcl_irrelevance": null,
|
|
3749
|
+
"arena_rating": 1202.6459515220915,
|
|
3750
|
+
"arena_rank": 304,
|
|
3751
|
+
"composite": 0.18766756032171583,
|
|
3752
|
+
"composite_rank": 348
|
|
3753
|
+
},
|
|
3754
|
+
{
|
|
3755
|
+
"name": "Falcon3-10B-Instruct (FC)",
|
|
3756
|
+
"norm": "falcon3-10b-instruct",
|
|
3757
|
+
"bfcl_overall": 27.01,
|
|
3758
|
+
"bfcl_multi_turn": 6.5,
|
|
3759
|
+
"bfcl_irrelevance": 32.09,
|
|
3760
|
+
"composite": 0.1851851851851852,
|
|
3761
|
+
"composite_rank": 349
|
|
3762
|
+
},
|
|
3763
|
+
{
|
|
3764
|
+
"name": "gemma-2-2b-it",
|
|
3765
|
+
"norm": "gemma-2-2b-it",
|
|
3766
|
+
"bfcl_overall": null,
|
|
3767
|
+
"bfcl_multi_turn": null,
|
|
3768
|
+
"bfcl_irrelevance": null,
|
|
3769
|
+
"arena_rating": 1199.7912701073512,
|
|
3770
|
+
"arena_rank": 305,
|
|
3771
|
+
"composite": 0.18498659517426275,
|
|
3772
|
+
"composite_rank": 350
|
|
3773
|
+
},
|
|
3774
|
+
{
|
|
3775
|
+
"name": "phi-3-medium-4k-instruct",
|
|
3776
|
+
"norm": "phi-3-medium-4k-instruct",
|
|
3777
|
+
"bfcl_overall": null,
|
|
3778
|
+
"bfcl_multi_turn": null,
|
|
3779
|
+
"bfcl_irrelevance": null,
|
|
3780
|
+
"arena_rating": 1197.1669138796503,
|
|
3781
|
+
"arena_rank": 306,
|
|
3782
|
+
"composite": 0.18230563002680966,
|
|
3783
|
+
"composite_rank": 351
|
|
3784
|
+
},
|
|
3785
|
+
{
|
|
3786
|
+
"name": "Llama-3.1-8B-Instruct (Prompt)",
|
|
3787
|
+
"norm": "llama-3.1-8b-instruct",
|
|
3788
|
+
"bfcl_overall": 25.83,
|
|
3789
|
+
"bfcl_multi_turn": 11.12,
|
|
3790
|
+
"bfcl_irrelevance": 42.7,
|
|
3791
|
+
"arena_rating": 1211.2868807345133,
|
|
3792
|
+
"arena_rank": 301,
|
|
3793
|
+
"composite": 0.18164366332373486,
|
|
3794
|
+
"composite_rank": 352
|
|
3795
|
+
},
|
|
3796
|
+
{
|
|
3797
|
+
"name": "mixtral-8x7b-instruct-v0.1",
|
|
3798
|
+
"norm": "mixtral-8x7b-instruct-v0.1",
|
|
3799
|
+
"bfcl_overall": null,
|
|
3800
|
+
"bfcl_multi_turn": null,
|
|
3801
|
+
"bfcl_irrelevance": null,
|
|
3802
|
+
"arena_rating": 1196.318472809937,
|
|
3803
|
+
"arena_rank": 307,
|
|
3804
|
+
"composite": 0.17962466487935658,
|
|
3805
|
+
"composite_rank": 353
|
|
3806
|
+
},
|
|
3807
|
+
{
|
|
3808
|
+
"name": "dbrx-instruct-preview",
|
|
3809
|
+
"norm": "dbrx-instruct-preview",
|
|
3810
|
+
"bfcl_overall": null,
|
|
3811
|
+
"bfcl_multi_turn": null,
|
|
3812
|
+
"bfcl_irrelevance": null,
|
|
3813
|
+
"arena_rating": 1194.4939055947852,
|
|
3814
|
+
"arena_rank": 308,
|
|
3815
|
+
"composite": 0.1769436997319035,
|
|
3816
|
+
"composite_rank": 354
|
|
3817
|
+
},
|
|
3818
|
+
{
|
|
3819
|
+
"name": "internlm2_5-20b-chat",
|
|
3820
|
+
"norm": "internlm2_5-20b-chat",
|
|
3821
|
+
"bfcl_overall": null,
|
|
3822
|
+
"bfcl_multi_turn": null,
|
|
3823
|
+
"bfcl_irrelevance": null,
|
|
3824
|
+
"arena_rating": 1190.5413368666195,
|
|
3825
|
+
"arena_rank": 309,
|
|
3826
|
+
"composite": 0.1742627345844504,
|
|
3827
|
+
"composite_rank": 355
|
|
3828
|
+
},
|
|
3829
|
+
{
|
|
3830
|
+
"name": "qwen1.5-14b-chat",
|
|
3831
|
+
"norm": "qwen1.5-14b-chat",
|
|
3832
|
+
"bfcl_overall": null,
|
|
3833
|
+
"bfcl_multi_turn": null,
|
|
3834
|
+
"bfcl_irrelevance": null,
|
|
3835
|
+
"arena_rating": 1190.2907607099185,
|
|
3836
|
+
"arena_rank": 310,
|
|
3837
|
+
"composite": 0.17158176943699732,
|
|
3838
|
+
"composite_rank": 356
|
|
3839
|
+
},
|
|
3840
|
+
{
|
|
3841
|
+
"name": "wizardlm-70b",
|
|
3842
|
+
"norm": "wizardlm-70b",
|
|
3843
|
+
"bfcl_overall": null,
|
|
3844
|
+
"bfcl_multi_turn": null,
|
|
3845
|
+
"bfcl_irrelevance": null,
|
|
3846
|
+
"arena_rating": 1183.9143414791088,
|
|
3847
|
+
"arena_rank": 311,
|
|
3848
|
+
"composite": 0.16890080428954424,
|
|
3849
|
+
"composite_rank": 357
|
|
3850
|
+
},
|
|
3851
|
+
{
|
|
3852
|
+
"name": "deepseek-llm-67b-chat",
|
|
3853
|
+
"norm": "deepseek-llm-67b-chat",
|
|
3854
|
+
"bfcl_overall": null,
|
|
3855
|
+
"bfcl_multi_turn": null,
|
|
3856
|
+
"bfcl_irrelevance": null,
|
|
3857
|
+
"arena_rating": 1183.8571008921017,
|
|
3858
|
+
"arena_rank": 312,
|
|
3859
|
+
"composite": 0.16621983914209115,
|
|
3860
|
+
"composite_rank": 358
|
|
3861
|
+
},
|
|
3862
|
+
{
|
|
3863
|
+
"name": "yi-34b-chat",
|
|
3864
|
+
"norm": "yi-34b-chat",
|
|
3865
|
+
"bfcl_overall": null,
|
|
3866
|
+
"bfcl_multi_turn": null,
|
|
3867
|
+
"bfcl_irrelevance": null,
|
|
3868
|
+
"arena_rating": 1183.105074664547,
|
|
3869
|
+
"arena_rank": 313,
|
|
3870
|
+
"composite": 0.16353887399463807,
|
|
3871
|
+
"composite_rank": 359
|
|
3872
|
+
},
|
|
3873
|
+
{
|
|
3874
|
+
"name": "granite-3.0-8b-instruct",
|
|
3875
|
+
"norm": "granite-3.0-8b-instruct",
|
|
3876
|
+
"bfcl_overall": null,
|
|
3877
|
+
"bfcl_multi_turn": null,
|
|
3878
|
+
"bfcl_irrelevance": null,
|
|
3879
|
+
"arena_rating": 1181.9793317799847,
|
|
3880
|
+
"arena_rank": 314,
|
|
3881
|
+
"composite": 0.16085790884718498,
|
|
3882
|
+
"composite_rank": 360
|
|
3883
|
+
},
|
|
3884
|
+
{
|
|
3885
|
+
"name": "Gemma-3-4b-it (Prompt)",
|
|
3886
|
+
"norm": "gemma-3-4b-it",
|
|
3887
|
+
"bfcl_overall": 19.62,
|
|
3888
|
+
"bfcl_multi_turn": 0.38,
|
|
3889
|
+
"bfcl_irrelevance": 53.94,
|
|
3890
|
+
"arena_rating": 1303.3234681833749,
|
|
3891
|
+
"arena_rank": 245,
|
|
3892
|
+
"composite": 0.16053520007943603,
|
|
3893
|
+
"composite_rank": 361
|
|
3894
|
+
},
|
|
3895
|
+
{
|
|
3896
|
+
"name": "openchat-3.5",
|
|
3897
|
+
"norm": "openchat-3.5",
|
|
3898
|
+
"bfcl_overall": null,
|
|
3899
|
+
"bfcl_multi_turn": null,
|
|
3900
|
+
"bfcl_irrelevance": null,
|
|
3901
|
+
"arena_rating": 1181.8764315163885,
|
|
3902
|
+
"arena_rank": 315,
|
|
3903
|
+
"composite": 0.1581769436997319,
|
|
3904
|
+
"composite_rank": 362
|
|
3905
|
+
},
|
|
3906
|
+
{
|
|
3907
|
+
"name": "openchat-3.5-0106",
|
|
3908
|
+
"norm": "openchat-3.5-0106",
|
|
3909
|
+
"bfcl_overall": null,
|
|
3910
|
+
"bfcl_multi_turn": null,
|
|
3911
|
+
"bfcl_irrelevance": null,
|
|
3912
|
+
"arena_rating": 1181.7327786706794,
|
|
3913
|
+
"arena_rank": 316,
|
|
3914
|
+
"composite": 0.1554959785522788,
|
|
3915
|
+
"composite_rank": 363
|
|
3916
|
+
},
|
|
3917
|
+
{
|
|
3918
|
+
"name": "gemma-1.1-7b-it",
|
|
3919
|
+
"norm": "gemma-1.1-7b-it",
|
|
3920
|
+
"bfcl_overall": null,
|
|
3921
|
+
"bfcl_multi_turn": null,
|
|
3922
|
+
"bfcl_irrelevance": null,
|
|
3923
|
+
"arena_rating": 1181.4979121695605,
|
|
3924
|
+
"arena_rank": 317,
|
|
3925
|
+
"composite": 0.15281501340482573,
|
|
3926
|
+
"composite_rank": 364
|
|
3927
|
+
},
|
|
3928
|
+
{
|
|
3929
|
+
"name": "snowflake-arctic-instruct",
|
|
3930
|
+
"norm": "snowflake-arctic-instruct",
|
|
3931
|
+
"bfcl_overall": null,
|
|
3932
|
+
"bfcl_multi_turn": null,
|
|
3933
|
+
"bfcl_irrelevance": null,
|
|
3934
|
+
"arena_rating": 1178.9892247919042,
|
|
3935
|
+
"arena_rank": 318,
|
|
3936
|
+
"composite": 0.15013404825737264,
|
|
3937
|
+
"composite_rank": 365
|
|
3938
|
+
},
|
|
3939
|
+
{
|
|
3940
|
+
"name": "granite-3.1-2b-instruct",
|
|
3941
|
+
"norm": "granite-3.1-2b-instruct",
|
|
3942
|
+
"bfcl_overall": null,
|
|
3943
|
+
"bfcl_multi_turn": null,
|
|
3944
|
+
"bfcl_irrelevance": null,
|
|
3945
|
+
"arena_rating": 1178.3086752395338,
|
|
3946
|
+
"arena_rank": 319,
|
|
3947
|
+
"composite": 0.14745308310991956,
|
|
3948
|
+
"composite_rank": 366
|
|
3949
|
+
},
|
|
3950
|
+
{
|
|
3951
|
+
"name": "tulu-2-dpo-70b",
|
|
3952
|
+
"norm": "tulu-2-dpo-70b",
|
|
3953
|
+
"bfcl_overall": null,
|
|
3954
|
+
"bfcl_multi_turn": null,
|
|
3955
|
+
"bfcl_irrelevance": null,
|
|
3956
|
+
"arena_rating": 1176.9685915901757,
|
|
3957
|
+
"arena_rank": 320,
|
|
3958
|
+
"composite": 0.14477211796246647,
|
|
3959
|
+
"composite_rank": 367
|
|
3960
|
+
},
|
|
3961
|
+
{
|
|
3962
|
+
"name": "openhermes-2.5-mistral-7b",
|
|
3963
|
+
"norm": "openhermes-2.5-mistral-7b",
|
|
3964
|
+
"bfcl_overall": null,
|
|
3965
|
+
"bfcl_multi_turn": null,
|
|
3966
|
+
"bfcl_irrelevance": null,
|
|
3967
|
+
"arena_rating": 1174.8263358647766,
|
|
3968
|
+
"arena_rank": 321,
|
|
3969
|
+
"composite": 0.1420911528150134,
|
|
3970
|
+
"composite_rank": 368
|
|
3971
|
+
},
|
|
3972
|
+
{
|
|
3973
|
+
"name": "vicuna-33b",
|
|
3974
|
+
"norm": "vicuna-33b",
|
|
3975
|
+
"bfcl_overall": null,
|
|
3976
|
+
"bfcl_multi_turn": null,
|
|
3977
|
+
"bfcl_irrelevance": null,
|
|
3978
|
+
"arena_rating": 1172.0628515217222,
|
|
3979
|
+
"arena_rank": 322,
|
|
3980
|
+
"composite": 0.1394101876675603,
|
|
3981
|
+
"composite_rank": 369
|
|
3982
|
+
},
|
|
3983
|
+
{
|
|
3984
|
+
"name": "starling-lm-7b-beta",
|
|
3985
|
+
"norm": "starling-lm-7b-beta",
|
|
3986
|
+
"bfcl_overall": null,
|
|
3987
|
+
"bfcl_multi_turn": null,
|
|
3988
|
+
"bfcl_irrelevance": null,
|
|
3989
|
+
"arena_rating": 1170.575662013345,
|
|
3990
|
+
"arena_rank": 323,
|
|
3991
|
+
"composite": 0.13672922252010722,
|
|
3992
|
+
"composite_rank": 370
|
|
3993
|
+
},
|
|
3994
|
+
{
|
|
3995
|
+
"name": "phi-3-small-8k-instruct",
|
|
3996
|
+
"norm": "phi-3-small-8k-instruct",
|
|
3997
|
+
"bfcl_overall": null,
|
|
3998
|
+
"bfcl_multi_turn": null,
|
|
3999
|
+
"bfcl_irrelevance": null,
|
|
4000
|
+
"arena_rating": 1170.3344746431512,
|
|
4001
|
+
"arena_rank": 324,
|
|
4002
|
+
"composite": 0.13404825737265413,
|
|
4003
|
+
"composite_rank": 371
|
|
4004
|
+
},
|
|
4005
|
+
{
|
|
4006
|
+
"name": "Falcon3-7B-Instruct (FC)",
|
|
4007
|
+
"norm": "falcon3-7b-instruct",
|
|
4008
|
+
"bfcl_overall": 24.03,
|
|
4009
|
+
"bfcl_multi_turn": 5,
|
|
4010
|
+
"bfcl_irrelevance": 31.99,
|
|
4011
|
+
"composite": 0.1316872427983539,
|
|
4012
|
+
"composite_rank": 372
|
|
4013
|
+
},
|
|
4014
|
+
{
|
|
4015
|
+
"name": "llama-2-70b-chat",
|
|
4016
|
+
"norm": "llama-2-70b-chat",
|
|
4017
|
+
"bfcl_overall": null,
|
|
4018
|
+
"bfcl_multi_turn": null,
|
|
4019
|
+
"bfcl_irrelevance": null,
|
|
4020
|
+
"arena_rating": 1169.9802477812777,
|
|
4021
|
+
"arena_rank": 325,
|
|
4022
|
+
"composite": 0.13136729222520105,
|
|
4023
|
+
"composite_rank": 373
|
|
4024
|
+
},
|
|
4025
|
+
{
|
|
4026
|
+
"name": "starling-lm-7b-alpha",
|
|
4027
|
+
"norm": "starling-lm-7b-alpha",
|
|
4028
|
+
"bfcl_overall": null,
|
|
4029
|
+
"bfcl_multi_turn": null,
|
|
4030
|
+
"bfcl_irrelevance": null,
|
|
4031
|
+
"arena_rating": 1166.6746449268628,
|
|
4032
|
+
"arena_rank": 326,
|
|
4033
|
+
"composite": 0.12868632707774796,
|
|
4034
|
+
"composite_rank": 374
|
|
4035
|
+
},
|
|
4036
|
+
{
|
|
4037
|
+
"name": "nous-hermes-2-mixtral-8x7b-dpo",
|
|
4038
|
+
"norm": "nous-hermes-2-mixtral-8x7b-dpo",
|
|
4039
|
+
"bfcl_overall": null,
|
|
4040
|
+
"bfcl_multi_turn": null,
|
|
4041
|
+
"bfcl_irrelevance": null,
|
|
4042
|
+
"arena_rating": 1163.7910210387358,
|
|
4043
|
+
"arena_rank": 328,
|
|
4044
|
+
"composite": 0.1233243967828418,
|
|
4045
|
+
"composite_rank": 375
|
|
4046
|
+
},
|
|
4047
|
+
{
|
|
4048
|
+
"name": "granite-3.0-2b-instruct",
|
|
4049
|
+
"norm": "granite-3.0-2b-instruct",
|
|
4050
|
+
"bfcl_overall": null,
|
|
4051
|
+
"bfcl_multi_turn": null,
|
|
4052
|
+
"bfcl_irrelevance": null,
|
|
4053
|
+
"arena_rating": 1155.66814275337,
|
|
4054
|
+
"arena_rank": 329,
|
|
4055
|
+
"composite": 0.12064343163538871,
|
|
4056
|
+
"composite_rank": 376
|
|
4057
|
+
},
|
|
4058
|
+
{
|
|
4059
|
+
"name": "qwq-32b-preview",
|
|
4060
|
+
"norm": "qwq-32b-preview",
|
|
4061
|
+
"bfcl_overall": null,
|
|
4062
|
+
"bfcl_multi_turn": null,
|
|
4063
|
+
"bfcl_irrelevance": null,
|
|
4064
|
+
"arena_rating": 1154.7029120142595,
|
|
4065
|
+
"arena_rank": 330,
|
|
4066
|
+
"composite": 0.11796246648793562,
|
|
4067
|
+
"composite_rank": 377
|
|
4068
|
+
},
|
|
4069
|
+
{
|
|
4070
|
+
"name": "Llama-3.2-3B-Instruct (FC)",
|
|
4071
|
+
"norm": "llama-3.2-3b-instruct",
|
|
4072
|
+
"bfcl_overall": 21.95,
|
|
4073
|
+
"bfcl_multi_turn": 4,
|
|
4074
|
+
"bfcl_irrelevance": 52.06,
|
|
4075
|
+
"arena_rating": 1166.172117514411,
|
|
4076
|
+
"arena_rank": 327,
|
|
4077
|
+
"composite": 0.11792109356899347,
|
|
4078
|
+
"composite_rank": 378
|
|
4079
|
+
},
|
|
4080
|
+
{
|
|
4081
|
+
"name": "llama2-70b-steerlm-chat",
|
|
4082
|
+
"norm": "llama2-70b-steerlm-chat",
|
|
4083
|
+
"bfcl_overall": null,
|
|
4084
|
+
"bfcl_multi_turn": null,
|
|
4085
|
+
"bfcl_irrelevance": null,
|
|
4086
|
+
"arena_rating": 1153.998831181928,
|
|
4087
|
+
"arena_rank": 331,
|
|
4088
|
+
"composite": 0.11528150134048254,
|
|
4089
|
+
"composite_rank": 379
|
|
4090
|
+
},
|
|
4091
|
+
{
|
|
4092
|
+
"name": "solar-10.7b-instruct-v1.0",
|
|
4093
|
+
"norm": "solar-10.7b-instruct-v1.0",
|
|
4094
|
+
"bfcl_overall": null,
|
|
4095
|
+
"bfcl_multi_turn": null,
|
|
4096
|
+
"bfcl_irrelevance": null,
|
|
4097
|
+
"arena_rating": 1151.5252964122224,
|
|
4098
|
+
"arena_rank": 332,
|
|
4099
|
+
"composite": 0.11260053619302945,
|
|
4100
|
+
"composite_rank": 380
|
|
4101
|
+
},
|
|
4102
|
+
{
|
|
4103
|
+
"name": "dolphin-2.2.1-mistral-7b",
|
|
4104
|
+
"norm": "dolphin-2.2.1-mistral-7b",
|
|
4105
|
+
"bfcl_overall": null,
|
|
4106
|
+
"bfcl_multi_turn": null,
|
|
4107
|
+
"bfcl_irrelevance": null,
|
|
4108
|
+
"arena_rating": 1151.3488389774204,
|
|
4109
|
+
"arena_rank": 333,
|
|
4110
|
+
"composite": 0.10991957104557637,
|
|
4111
|
+
"composite_rank": 381
|
|
4112
|
+
},
|
|
4113
|
+
{
|
|
4114
|
+
"name": "mpt-30b-chat",
|
|
4115
|
+
"norm": "mpt-30b-chat",
|
|
4116
|
+
"bfcl_overall": null,
|
|
4117
|
+
"bfcl_multi_turn": null,
|
|
4118
|
+
"bfcl_irrelevance": null,
|
|
4119
|
+
"arena_rating": 1149.6570784001462,
|
|
4120
|
+
"arena_rank": 334,
|
|
4121
|
+
"composite": 0.10723860589812328,
|
|
4122
|
+
"composite_rank": 382
|
|
4123
|
+
},
|
|
4124
|
+
{
|
|
4125
|
+
"name": "mistral-7b-instruct-v0.2",
|
|
4126
|
+
"norm": "mistral-7b-instruct-v0.2",
|
|
4127
|
+
"bfcl_overall": null,
|
|
4128
|
+
"bfcl_multi_turn": null,
|
|
4129
|
+
"bfcl_irrelevance": null,
|
|
4130
|
+
"arena_rating": 1148.6504527964096,
|
|
4131
|
+
"arena_rank": 335,
|
|
4132
|
+
"composite": 0.1045576407506702,
|
|
4133
|
+
"composite_rank": 383
|
|
4134
|
+
},
|
|
4135
|
+
{
|
|
4136
|
+
"name": "wizardlm-13b",
|
|
4137
|
+
"norm": "wizardlm-13b",
|
|
4138
|
+
"bfcl_overall": null,
|
|
4139
|
+
"bfcl_multi_turn": null,
|
|
4140
|
+
"bfcl_irrelevance": null,
|
|
4141
|
+
"arena_rating": 1148.5786047409663,
|
|
4142
|
+
"arena_rank": 336,
|
|
4143
|
+
"composite": 0.10187667560321712,
|
|
4144
|
+
"composite_rank": 384
|
|
4145
|
+
},
|
|
4146
|
+
{
|
|
4147
|
+
"name": "falcon-180b-chat",
|
|
4148
|
+
"norm": "falcon-180b-chat",
|
|
4149
|
+
"bfcl_overall": null,
|
|
4150
|
+
"bfcl_multi_turn": null,
|
|
4151
|
+
"bfcl_irrelevance": null,
|
|
4152
|
+
"arena_rating": 1146.8333513662371,
|
|
4153
|
+
"arena_rank": 337,
|
|
4154
|
+
"composite": 0.09919571045576403,
|
|
4155
|
+
"composite_rank": 385
|
|
4156
|
+
},
|
|
4157
|
+
{
|
|
4158
|
+
"name": "Granite-4.0-350m (FC)",
|
|
4159
|
+
"norm": "granite-4.0-350m",
|
|
4160
|
+
"bfcl_overall": 18.98,
|
|
4161
|
+
"bfcl_multi_turn": 2.5,
|
|
4162
|
+
"bfcl_irrelevance": 60.84,
|
|
4163
|
+
"composite": 0.09876543209876543,
|
|
4164
|
+
"composite_rank": 386
|
|
4165
|
+
},
|
|
4166
|
+
{
|
|
4167
|
+
"name": "qwen1.5-7b-chat",
|
|
4168
|
+
"norm": "qwen1.5-7b-chat",
|
|
4169
|
+
"bfcl_overall": null,
|
|
4170
|
+
"bfcl_multi_turn": null,
|
|
4171
|
+
"bfcl_irrelevance": null,
|
|
4172
|
+
"arena_rating": 1143.1188554425644,
|
|
4173
|
+
"arena_rank": 338,
|
|
4174
|
+
"composite": 0.09651474530831095,
|
|
4175
|
+
"composite_rank": 387
|
|
4176
|
+
},
|
|
4177
|
+
{
|
|
4178
|
+
"name": "phi-3-mini-4k-instruct-june-2024",
|
|
4179
|
+
"norm": "phi-3-mini-4k-instruct-june-2024",
|
|
4180
|
+
"bfcl_overall": null,
|
|
4181
|
+
"bfcl_multi_turn": null,
|
|
4182
|
+
"bfcl_irrelevance": null,
|
|
4183
|
+
"arena_rating": 1142.3618176235482,
|
|
4184
|
+
"arena_rank": 339,
|
|
4185
|
+
"composite": 0.09383378016085786,
|
|
4186
|
+
"composite_rank": 388
|
|
4187
|
+
},
|
|
4188
|
+
{
|
|
4189
|
+
"name": "llama-2-13b-chat",
|
|
4190
|
+
"norm": "llama-2-13b-chat",
|
|
4191
|
+
"bfcl_overall": null,
|
|
4192
|
+
"bfcl_multi_turn": null,
|
|
4193
|
+
"bfcl_irrelevance": null,
|
|
4194
|
+
"arena_rating": 1140.7478692899394,
|
|
4195
|
+
"arena_rank": 340,
|
|
4196
|
+
"composite": 0.09115281501340478,
|
|
4197
|
+
"composite_rank": 389
|
|
4198
|
+
},
|
|
4199
|
+
{
|
|
4200
|
+
"name": "Bielik-11B-v2.3-Instruct (Prompt)",
|
|
4201
|
+
"norm": "bielik-11b-v2.3-instruct",
|
|
4202
|
+
"bfcl_overall": 21.9,
|
|
4203
|
+
"bfcl_multi_turn": 2.62,
|
|
4204
|
+
"bfcl_irrelevance": 36.01,
|
|
4205
|
+
"composite": 0.09053497942386834,
|
|
4206
|
+
"composite_rank": 390
|
|
4207
|
+
},
|
|
4208
|
+
{
|
|
4209
|
+
"name": "vicuna-13b",
|
|
4210
|
+
"norm": "vicuna-13b",
|
|
4211
|
+
"bfcl_overall": null,
|
|
4212
|
+
"bfcl_multi_turn": null,
|
|
4213
|
+
"bfcl_irrelevance": null,
|
|
4214
|
+
"arena_rating": 1140.4369831276406,
|
|
4215
|
+
"arena_rank": 341,
|
|
4216
|
+
"composite": 0.08847184986595169,
|
|
4217
|
+
"composite_rank": 391
|
|
4218
|
+
},
|
|
4219
|
+
{
|
|
4220
|
+
"name": "qwen-14b-chat",
|
|
4221
|
+
"norm": "qwen-14b-chat",
|
|
4222
|
+
"bfcl_overall": null,
|
|
4223
|
+
"bfcl_multi_turn": null,
|
|
4224
|
+
"bfcl_irrelevance": null,
|
|
4225
|
+
"arena_rating": 1138.1537532502039,
|
|
4226
|
+
"arena_rank": 342,
|
|
4227
|
+
"composite": 0.0857908847184986,
|
|
4228
|
+
"composite_rank": 392
|
|
4229
|
+
},
|
|
4230
|
+
{
|
|
4231
|
+
"name": "palm-2",
|
|
4232
|
+
"norm": "palm-2",
|
|
4233
|
+
"bfcl_overall": null,
|
|
4234
|
+
"bfcl_multi_turn": null,
|
|
4235
|
+
"bfcl_irrelevance": null,
|
|
4236
|
+
"arena_rating": 1137.5998294163358,
|
|
4237
|
+
"arena_rank": 343,
|
|
4238
|
+
"composite": 0.08310991957104563,
|
|
4239
|
+
"composite_rank": 393
|
|
4240
|
+
},
|
|
4241
|
+
{
|
|
4242
|
+
"name": "gemma-7b-it",
|
|
4243
|
+
"norm": "gemma-7b-it",
|
|
4244
|
+
"bfcl_overall": null,
|
|
4245
|
+
"bfcl_multi_turn": null,
|
|
4246
|
+
"bfcl_irrelevance": null,
|
|
4247
|
+
"arena_rating": 1136.757512706434,
|
|
4248
|
+
"arena_rank": 344,
|
|
4249
|
+
"composite": 0.08042895442359255,
|
|
4250
|
+
"composite_rank": 394
|
|
4251
|
+
},
|
|
4252
|
+
{
|
|
4253
|
+
"name": "codellama-34b-instruct",
|
|
4254
|
+
"norm": "codellama-34b-instruct",
|
|
4255
|
+
"bfcl_overall": null,
|
|
4256
|
+
"bfcl_multi_turn": null,
|
|
4257
|
+
"bfcl_irrelevance": null,
|
|
4258
|
+
"arena_rating": 1135.943389208142,
|
|
4259
|
+
"arena_rank": 345,
|
|
4260
|
+
"composite": 0.07774798927613946,
|
|
4261
|
+
"composite_rank": 395
|
|
4262
|
+
},
|
|
4263
|
+
{
|
|
4264
|
+
"name": "zephyr-7b-beta",
|
|
4265
|
+
"norm": "zephyr-7b-beta",
|
|
4266
|
+
"bfcl_overall": null,
|
|
4267
|
+
"bfcl_multi_turn": null,
|
|
4268
|
+
"bfcl_irrelevance": null,
|
|
4269
|
+
"arena_rating": 1130.0442089324508,
|
|
4270
|
+
"arena_rank": 346,
|
|
4271
|
+
"composite": 0.07506702412868638,
|
|
4272
|
+
"composite_rank": 396
|
|
4273
|
+
},
|
|
4274
|
+
{
|
|
4275
|
+
"name": "phi-3-mini-128k-instruct",
|
|
4276
|
+
"norm": "phi-3-mini-128k-instruct",
|
|
4277
|
+
"bfcl_overall": null,
|
|
4278
|
+
"bfcl_multi_turn": null,
|
|
4279
|
+
"bfcl_irrelevance": null,
|
|
4280
|
+
"arena_rating": 1128.7918286507547,
|
|
4281
|
+
"arena_rank": 347,
|
|
4282
|
+
"composite": 0.07238605898123329,
|
|
4283
|
+
"composite_rank": 397
|
|
4284
|
+
},
|
|
4285
|
+
{
|
|
4286
|
+
"name": "phi-3-mini-4k-instruct",
|
|
4287
|
+
"norm": "phi-3-mini-4k-instruct",
|
|
4288
|
+
"bfcl_overall": null,
|
|
4289
|
+
"bfcl_multi_turn": null,
|
|
4290
|
+
"bfcl_irrelevance": null,
|
|
4291
|
+
"arena_rating": 1127.4733381558824,
|
|
4292
|
+
"arena_rank": 348,
|
|
4293
|
+
"composite": 0.06970509383378021,
|
|
4294
|
+
"composite_rank": 398
|
|
4295
|
+
},
|
|
4296
|
+
{
|
|
4297
|
+
"name": "guanaco-33b",
|
|
4298
|
+
"norm": "guanaco-33b",
|
|
4299
|
+
"bfcl_overall": null,
|
|
4300
|
+
"bfcl_multi_turn": null,
|
|
4301
|
+
"bfcl_irrelevance": null,
|
|
4302
|
+
"arena_rating": 1126.5339092473082,
|
|
4303
|
+
"arena_rank": 349,
|
|
4304
|
+
"composite": 0.06702412868632712,
|
|
4305
|
+
"composite_rank": 399
|
|
4306
|
+
},
|
|
4307
|
+
{
|
|
4308
|
+
"name": "zephyr-7b-alpha",
|
|
4309
|
+
"norm": "zephyr-7b-alpha",
|
|
4310
|
+
"bfcl_overall": null,
|
|
4311
|
+
"bfcl_multi_turn": null,
|
|
4312
|
+
"bfcl_irrelevance": null,
|
|
4313
|
+
"arena_rating": 1126.0603824768464,
|
|
4314
|
+
"arena_rank": 350,
|
|
4315
|
+
"composite": 0.06434316353887404,
|
|
4316
|
+
"composite_rank": 400
|
|
4317
|
+
},
|
|
4318
|
+
{
|
|
4319
|
+
"name": "stripedhyena-nous-7b",
|
|
4320
|
+
"norm": "stripedhyena-nous-7b",
|
|
4321
|
+
"bfcl_overall": null,
|
|
4322
|
+
"bfcl_multi_turn": null,
|
|
4323
|
+
"bfcl_irrelevance": null,
|
|
4324
|
+
"arena_rating": 1120.5015886062524,
|
|
4325
|
+
"arena_rank": 351,
|
|
4326
|
+
"composite": 0.06166219839142095,
|
|
4327
|
+
"composite_rank": 401
|
|
4328
|
+
},
|
|
4329
|
+
{
|
|
4330
|
+
"name": "codellama-70b-instruct",
|
|
4331
|
+
"norm": "codellama-70b-instruct",
|
|
4332
|
+
"bfcl_overall": null,
|
|
4333
|
+
"bfcl_multi_turn": null,
|
|
4334
|
+
"bfcl_irrelevance": null,
|
|
4335
|
+
"arena_rating": 1118.4473870792074,
|
|
4336
|
+
"arena_rank": 352,
|
|
4337
|
+
"composite": 0.05898123324396787,
|
|
4338
|
+
"composite_rank": 402
|
|
4339
|
+
},
|
|
4340
|
+
{
|
|
4341
|
+
"name": "gemma-1.1-2b-it",
|
|
4342
|
+
"norm": "gemma-1.1-2b-it",
|
|
4343
|
+
"bfcl_overall": null,
|
|
4344
|
+
"bfcl_multi_turn": null,
|
|
4345
|
+
"bfcl_irrelevance": null,
|
|
4346
|
+
"arena_rating": 1115.4863902943755,
|
|
4347
|
+
"arena_rank": 353,
|
|
4348
|
+
"composite": 0.05630026809651478,
|
|
4349
|
+
"composite_rank": 403
|
|
4350
|
+
},
|
|
4351
|
+
{
|
|
4352
|
+
"name": "vicuna-7b",
|
|
4353
|
+
"norm": "vicuna-7b",
|
|
4354
|
+
"bfcl_overall": null,
|
|
4355
|
+
"bfcl_multi_turn": null,
|
|
4356
|
+
"bfcl_irrelevance": null,
|
|
4357
|
+
"arena_rating": 1114.1864972201056,
|
|
4358
|
+
"arena_rank": 354,
|
|
4359
|
+
"composite": 0.0536193029490617,
|
|
4360
|
+
"composite_rank": 404
|
|
4361
|
+
},
|
|
4362
|
+
{
|
|
4363
|
+
"name": "smollm2-1.7b-instruct",
|
|
4364
|
+
"norm": "smollm2-1.7b-instruct",
|
|
4365
|
+
"bfcl_overall": null,
|
|
4366
|
+
"bfcl_multi_turn": null,
|
|
4367
|
+
"bfcl_irrelevance": null,
|
|
4368
|
+
"arena_rating": 1113.803148517482,
|
|
4369
|
+
"arena_rank": 355,
|
|
4370
|
+
"composite": 0.05093833780160861,
|
|
4371
|
+
"composite_rank": 405
|
|
4372
|
+
},
|
|
4373
|
+
{
|
|
4374
|
+
"name": "Falcon3-3B-Instruct (FC)",
|
|
4375
|
+
"norm": "falcon3-3b-instruct",
|
|
4376
|
+
"bfcl_overall": 16.25,
|
|
4377
|
+
"bfcl_multi_turn": 1,
|
|
4378
|
+
"bfcl_irrelevance": 32.92,
|
|
4379
|
+
"composite": 0.04938271604938275,
|
|
4380
|
+
"composite_rank": 406
|
|
4381
|
+
},
|
|
4382
|
+
{
|
|
4383
|
+
"name": "Llama-3.2-1B-Instruct (FC)",
|
|
4384
|
+
"norm": "llama-3.2-1b-instruct",
|
|
4385
|
+
"bfcl_overall": 10.82,
|
|
4386
|
+
"bfcl_multi_turn": 0,
|
|
4387
|
+
"bfcl_irrelevance": 51.57,
|
|
4388
|
+
"arena_rating": 1110.5392295900344,
|
|
4389
|
+
"arena_rank": 356,
|
|
4390
|
+
"composite": 0.04601496044748951,
|
|
4391
|
+
"composite_rank": 407
|
|
4392
|
+
},
|
|
4393
|
+
{
|
|
4394
|
+
"name": "mistral-7b-instruct",
|
|
4395
|
+
"norm": "mistral-7b-instruct",
|
|
4396
|
+
"bfcl_overall": null,
|
|
4397
|
+
"bfcl_multi_turn": null,
|
|
4398
|
+
"bfcl_irrelevance": null,
|
|
4399
|
+
"arena_rating": 1109.1922083638276,
|
|
4400
|
+
"arena_rank": 357,
|
|
4401
|
+
"composite": 0.04557640750670244,
|
|
4402
|
+
"composite_rank": 408
|
|
4403
|
+
},
|
|
4404
|
+
{
|
|
4405
|
+
"name": "llama-2-7b-chat",
|
|
4406
|
+
"norm": "llama-2-7b-chat",
|
|
4407
|
+
"bfcl_overall": null,
|
|
4408
|
+
"bfcl_multi_turn": null,
|
|
4409
|
+
"bfcl_irrelevance": null,
|
|
4410
|
+
"arena_rating": 1107.2913394447298,
|
|
4411
|
+
"arena_rank": 358,
|
|
4412
|
+
"composite": 0.04289544235924936,
|
|
4413
|
+
"composite_rank": 409
|
|
4414
|
+
},
|
|
4415
|
+
{
|
|
4416
|
+
"name": "gemma-2b-it",
|
|
4417
|
+
"norm": "gemma-2b-it",
|
|
4418
|
+
"bfcl_overall": null,
|
|
4419
|
+
"bfcl_multi_turn": null,
|
|
4420
|
+
"bfcl_irrelevance": null,
|
|
4421
|
+
"arena_rating": 1092.5237624264591,
|
|
4422
|
+
"arena_rank": 359,
|
|
4423
|
+
"composite": 0.04021447721179627,
|
|
4424
|
+
"composite_rank": 410
|
|
4425
|
+
},
|
|
4426
|
+
{
|
|
4427
|
+
"name": "qwen1.5-4b-chat",
|
|
4428
|
+
"norm": "qwen1.5-4b-chat",
|
|
4429
|
+
"bfcl_overall": null,
|
|
4430
|
+
"bfcl_multi_turn": null,
|
|
4431
|
+
"bfcl_irrelevance": null,
|
|
4432
|
+
"arena_rating": 1089.849228489257,
|
|
4433
|
+
"arena_rank": 360,
|
|
4434
|
+
"composite": 0.03753351206434319,
|
|
4435
|
+
"composite_rank": 411
|
|
4436
|
+
},
|
|
4437
|
+
{
|
|
4438
|
+
"name": "olmo-7b-instruct",
|
|
4439
|
+
"norm": "olmo-7b-instruct",
|
|
4440
|
+
"bfcl_overall": null,
|
|
4441
|
+
"bfcl_multi_turn": null,
|
|
4442
|
+
"bfcl_irrelevance": null,
|
|
4443
|
+
"arena_rating": 1073.1916791365713,
|
|
4444
|
+
"arena_rank": 361,
|
|
4445
|
+
"composite": 0.034852546916890104,
|
|
4446
|
+
"composite_rank": 412
|
|
4447
|
+
},
|
|
4448
|
+
{
|
|
4449
|
+
"name": "koala-13b",
|
|
4450
|
+
"norm": "koala-13b",
|
|
4451
|
+
"bfcl_overall": null,
|
|
4452
|
+
"bfcl_multi_turn": null,
|
|
4453
|
+
"bfcl_irrelevance": null,
|
|
4454
|
+
"arena_rating": 1069.873809789131,
|
|
4455
|
+
"arena_rank": 362,
|
|
4456
|
+
"composite": 0.03217158176943702,
|
|
4457
|
+
"composite_rank": 413
|
|
4458
|
+
},
|
|
4459
|
+
{
|
|
4460
|
+
"name": "alpaca-13b",
|
|
4461
|
+
"norm": "alpaca-13b",
|
|
4462
|
+
"bfcl_overall": null,
|
|
4463
|
+
"bfcl_multi_turn": null,
|
|
4464
|
+
"bfcl_irrelevance": null,
|
|
4465
|
+
"arena_rating": 1068.2560456241806,
|
|
4466
|
+
"arena_rank": 363,
|
|
4467
|
+
"composite": 0.029490616621983934,
|
|
4468
|
+
"composite_rank": 414
|
|
4469
|
+
},
|
|
4470
|
+
{
|
|
4471
|
+
"name": "gpt4all-13b-snoozy",
|
|
4472
|
+
"norm": "gpt4all-13b-snoozy",
|
|
4473
|
+
"bfcl_overall": null,
|
|
4474
|
+
"bfcl_multi_turn": null,
|
|
4475
|
+
"bfcl_irrelevance": null,
|
|
4476
|
+
"arena_rating": 1066.159434038247,
|
|
4477
|
+
"arena_rank": 364,
|
|
4478
|
+
"composite": 0.02680965147453085,
|
|
4479
|
+
"composite_rank": 415
|
|
4480
|
+
},
|
|
4481
|
+
{
|
|
4482
|
+
"name": "mpt-7b-chat",
|
|
4483
|
+
"norm": "mpt-7b-chat",
|
|
4484
|
+
"bfcl_overall": null,
|
|
4485
|
+
"bfcl_multi_turn": null,
|
|
4486
|
+
"bfcl_irrelevance": null,
|
|
4487
|
+
"arena_rating": 1061.9497004362443,
|
|
4488
|
+
"arena_rank": 365,
|
|
4489
|
+
"composite": 0.024128686327077764,
|
|
4490
|
+
"composite_rank": 416
|
|
4491
|
+
},
|
|
4492
|
+
{
|
|
4493
|
+
"name": "chatglm3-6b",
|
|
4494
|
+
"norm": "chatglm3-6b",
|
|
4495
|
+
"bfcl_overall": null,
|
|
4496
|
+
"bfcl_multi_turn": null,
|
|
4497
|
+
"bfcl_irrelevance": null,
|
|
4498
|
+
"arena_rating": 1055.452151509097,
|
|
4499
|
+
"arena_rank": 366,
|
|
4500
|
+
"composite": 0.02144772117962468,
|
|
4501
|
+
"composite_rank": 417
|
|
4502
|
+
},
|
|
4503
|
+
{
|
|
4504
|
+
"name": "rwkv-4-raven-14b",
|
|
4505
|
+
"norm": "rwkv-4-raven-14b",
|
|
4506
|
+
"bfcl_overall": null,
|
|
4507
|
+
"bfcl_multi_turn": null,
|
|
4508
|
+
"bfcl_irrelevance": null,
|
|
4509
|
+
"arena_rating": 1041.08747299619,
|
|
4510
|
+
"arena_rank": 367,
|
|
4511
|
+
"composite": 0.018766756032171594,
|
|
4512
|
+
"composite_rank": 418
|
|
4513
|
+
},
|
|
4514
|
+
{
|
|
4515
|
+
"name": "chatglm2-6b",
|
|
4516
|
+
"norm": "chatglm2-6b",
|
|
4517
|
+
"bfcl_overall": null,
|
|
4518
|
+
"bfcl_multi_turn": null,
|
|
4519
|
+
"bfcl_irrelevance": null,
|
|
4520
|
+
"arena_rating": 1023.6362873762223,
|
|
4521
|
+
"arena_rank": 368,
|
|
4522
|
+
"composite": 0.01608579088471851,
|
|
4523
|
+
"composite_rank": 419
|
|
4524
|
+
},
|
|
4525
|
+
{
|
|
4526
|
+
"name": "oasst-pythia-12b",
|
|
4527
|
+
"norm": "oasst-pythia-12b",
|
|
4528
|
+
"bfcl_overall": null,
|
|
4529
|
+
"bfcl_multi_turn": null,
|
|
4530
|
+
"bfcl_irrelevance": null,
|
|
4531
|
+
"arena_rating": 1022.0665185356308,
|
|
4532
|
+
"arena_rank": 369,
|
|
4533
|
+
"composite": 0.013404825737265424,
|
|
4534
|
+
"composite_rank": 420
|
|
4535
|
+
},
|
|
4536
|
+
{
|
|
4537
|
+
"name": "Gemma-3-1b-it (Prompt)",
|
|
4538
|
+
"norm": "gemma-3-1b-it",
|
|
4539
|
+
"bfcl_overall": 7.17,
|
|
4540
|
+
"bfcl_multi_turn": 0,
|
|
4541
|
+
"bfcl_irrelevance": 33.18,
|
|
4542
|
+
"composite": 0.012345679012345697,
|
|
4543
|
+
"composite_rank": 421
|
|
4544
|
+
},
|
|
4545
|
+
{
|
|
4546
|
+
"name": "chatglm-6b",
|
|
4547
|
+
"norm": "chatglm-6b",
|
|
4548
|
+
"bfcl_overall": null,
|
|
4549
|
+
"bfcl_multi_turn": null,
|
|
4550
|
+
"bfcl_irrelevance": null,
|
|
4551
|
+
"arena_rating": 994.8509597544144,
|
|
4552
|
+
"arena_rank": 370,
|
|
4553
|
+
"composite": 0.01072386058981234,
|
|
4554
|
+
"composite_rank": 422
|
|
4555
|
+
},
|
|
4556
|
+
{
|
|
4557
|
+
"name": "fastchat-t5-3b",
|
|
4558
|
+
"norm": "fastchat-t5-3b",
|
|
4559
|
+
"bfcl_overall": null,
|
|
4560
|
+
"bfcl_multi_turn": null,
|
|
4561
|
+
"bfcl_irrelevance": null,
|
|
4562
|
+
"arena_rating": 991.2737070039473,
|
|
4563
|
+
"arena_rank": 371,
|
|
4564
|
+
"composite": 0.008042895442359255,
|
|
4565
|
+
"composite_rank": 423
|
|
4566
|
+
},
|
|
4567
|
+
{
|
|
4568
|
+
"name": "dolly-v2-12b",
|
|
4569
|
+
"norm": "dolly-v2-12b",
|
|
4570
|
+
"bfcl_overall": null,
|
|
4571
|
+
"bfcl_multi_turn": null,
|
|
4572
|
+
"bfcl_irrelevance": null,
|
|
4573
|
+
"arena_rating": 980.6581312307271,
|
|
4574
|
+
"arena_rank": 372,
|
|
4575
|
+
"composite": 0.00536193029490617,
|
|
4576
|
+
"composite_rank": 424
|
|
4577
|
+
},
|
|
4578
|
+
{
|
|
4579
|
+
"name": "llama-13b",
|
|
4580
|
+
"norm": "llama-13b",
|
|
4581
|
+
"bfcl_overall": null,
|
|
4582
|
+
"bfcl_multi_turn": null,
|
|
4583
|
+
"bfcl_irrelevance": null,
|
|
4584
|
+
"arena_rating": 973.1956192927316,
|
|
4585
|
+
"arena_rank": 373,
|
|
4586
|
+
"composite": 0.002680965147453085,
|
|
4587
|
+
"composite_rank": 425
|
|
4588
|
+
},
|
|
4589
|
+
{
|
|
4590
|
+
"name": "stablelm-tuned-alpha-7b",
|
|
4591
|
+
"norm": "stablelm-tuned-alpha-7b",
|
|
4592
|
+
"bfcl_overall": null,
|
|
4593
|
+
"bfcl_multi_turn": null,
|
|
4594
|
+
"bfcl_irrelevance": null,
|
|
4595
|
+
"arena_rating": 952.1121568169624,
|
|
4596
|
+
"arena_rank": 374,
|
|
4597
|
+
"composite": 0,
|
|
4598
|
+
"composite_rank": 426
|
|
4599
|
+
}
|
|
4600
|
+
]
|
|
4601
|
+
}
|