@botbotgo/better-call 0.1.2 → 0.1.4
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 +18 -16
- package/benchmarks/bfcl-real-remote-completed-summary.json +237 -1
- package/docs/banner.svg +2 -2
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# BetterCall
|
|
6
6
|
|
|
7
|
-
**One-line wrapper.
|
|
7
|
+
**One-line wrapper. Five full BFCL remote runs completed. Best: 73.4% → 83.8%.**
|
|
8
8
|
|
|
9
9
|
```ts
|
|
10
10
|
const tools = betterTools([searchTool, calculatorTool]);
|
|
@@ -123,28 +123,30 @@ Latest completed remote run artifact: `benchmarks/bfcl-real-remote-completed-sum
|
|
|
123
123
|
|
|
124
124
|
| Model | Completed cases | Raw | BetterCall repair | Accuracy lift | Request errors |
|
|
125
125
|
| --- | ---: | ---: | ---: | ---: | ---: |
|
|
126
|
+
| `granite4.1:3b` | 3,625 | 73.4% | 83.8% | +10.4pp | 25 |
|
|
126
127
|
| `qwen3:0.6b` | 3,625 | 55.5% | 63.6% | +8.2pp | 217 |
|
|
127
128
|
| `qwen3.5:0.8b` | 3,625 | 54.6% | 56.9% | +2.3pp | 901 |
|
|
129
|
+
| `qwen3.5:2b` | 3,625 | 53.9% | 54.9% | +1.0pp | 1,308 |
|
|
128
130
|
| `lfm2.5-thinking:latest` | 3,625 | 50.8% | 54.8% | +4.0pp | 1,142 |
|
|
129
131
|
|
|
130
|
-
Latest completed model category detail: `
|
|
132
|
+
Latest completed model category detail: `granite4.1:3b`.
|
|
131
133
|
|
|
132
134
|
| Category | Cases | Raw | BetterCall repair | Lift | Request errors |
|
|
133
135
|
| --- | ---: | ---: | ---: | ---: | ---: |
|
|
134
|
-
| `simple_python` | 400 |
|
|
135
|
-
| `simple_java` | 100 |
|
|
136
|
-
| `simple_javascript` | 50 |
|
|
137
|
-
| `multiple` | 200 |
|
|
138
|
-
| `parallel` | 200 |
|
|
139
|
-
| `parallel_multiple` | 200 |
|
|
140
|
-
| `irrelevance` | 240 |
|
|
141
|
-
| `live_simple` | 258 |
|
|
142
|
-
| `live_multiple` | 1,053 |
|
|
143
|
-
| `live_parallel` | 16 |
|
|
144
|
-
| `live_parallel_multiple` | 24 |
|
|
145
|
-
| `live_irrelevance` | 884 |
|
|
146
|
-
|
|
147
|
-
The strongest `
|
|
136
|
+
| `simple_python` | 400 | 86.5% | 86.8% | +0.3pp | 18 |
|
|
137
|
+
| `simple_java` | 100 | 70.0% | 70.0% | +0.0pp | 0 |
|
|
138
|
+
| `simple_javascript` | 50 | 72.0% | 72.0% | +0.0pp | 0 |
|
|
139
|
+
| `multiple` | 200 | 90.5% | 90.5% | +0.0pp | 0 |
|
|
140
|
+
| `parallel` | 200 | 83.0% | 83.0% | +0.0pp | 0 |
|
|
141
|
+
| `parallel_multiple` | 200 | 78.5% | 78.5% | +0.0pp | 0 |
|
|
142
|
+
| `irrelevance` | 240 | 67.1% | 100.0% | +32.9pp | 0 |
|
|
143
|
+
| `live_simple` | 258 | 74.0% | 74.0% | +0.0pp | 0 |
|
|
144
|
+
| `live_multiple` | 1,053 | 70.8% | 71.0% | +0.2pp | 0 |
|
|
145
|
+
| `live_parallel` | 16 | 68.8% | 68.8% | +0.0pp | 0 |
|
|
146
|
+
| `live_parallel_multiple` | 24 | 70.8% | 70.8% | +0.0pp | 0 |
|
|
147
|
+
| `live_irrelevance` | 884 | 65.5% | 99.0% | +33.5pp | 7 |
|
|
148
|
+
|
|
149
|
+
The strongest `granite4.1:3b` categories were no-tool-call tasks: `irrelevance` improved from 67.1% to 100.0%, and `live_irrelevance` improved from 65.5% to 99.0%.
|
|
148
150
|
|
|
149
151
|
Historical targeted wrapper benchmark:
|
|
150
152
|
|
|
@@ -2,8 +2,126 @@
|
|
|
2
2
|
"name": "BFCL v4 full remote Ollama runs",
|
|
3
3
|
"source": "Real model calls against all supported BFCL v4 single-turn tool-call categories completed in this repository",
|
|
4
4
|
"note": "Endpoint redacted. Scores count request errors/timeouts as incorrect. This is not an official BFCL leaderboard submission.",
|
|
5
|
-
"generatedAt": "2026-05-
|
|
5
|
+
"generatedAt": "2026-05-08T16:02:50.925Z",
|
|
6
6
|
"results": [
|
|
7
|
+
{
|
|
8
|
+
"model": "granite4.1:3b",
|
|
9
|
+
"total": 3625,
|
|
10
|
+
"rawCorrect": 2661,
|
|
11
|
+
"betterCorrect": 3039,
|
|
12
|
+
"errors": 25,
|
|
13
|
+
"repaired": 380,
|
|
14
|
+
"categories": [
|
|
15
|
+
{
|
|
16
|
+
"model": "granite4.1:3b",
|
|
17
|
+
"category": "simple_python",
|
|
18
|
+
"total": 400,
|
|
19
|
+
"rawCorrect": 346,
|
|
20
|
+
"betterCorrect": 347,
|
|
21
|
+
"errors": 18,
|
|
22
|
+
"repaired": 1
|
|
23
|
+
},
|
|
24
|
+
{
|
|
25
|
+
"model": "granite4.1:3b",
|
|
26
|
+
"category": "simple_java",
|
|
27
|
+
"total": 100,
|
|
28
|
+
"rawCorrect": 70,
|
|
29
|
+
"betterCorrect": 70,
|
|
30
|
+
"errors": 0,
|
|
31
|
+
"repaired": 1
|
|
32
|
+
},
|
|
33
|
+
{
|
|
34
|
+
"model": "granite4.1:3b",
|
|
35
|
+
"category": "simple_javascript",
|
|
36
|
+
"total": 50,
|
|
37
|
+
"rawCorrect": 36,
|
|
38
|
+
"betterCorrect": 36,
|
|
39
|
+
"errors": 0,
|
|
40
|
+
"repaired": 1
|
|
41
|
+
},
|
|
42
|
+
{
|
|
43
|
+
"model": "granite4.1:3b",
|
|
44
|
+
"category": "multiple",
|
|
45
|
+
"total": 200,
|
|
46
|
+
"rawCorrect": 181,
|
|
47
|
+
"betterCorrect": 181,
|
|
48
|
+
"errors": 0,
|
|
49
|
+
"repaired": 0
|
|
50
|
+
},
|
|
51
|
+
{
|
|
52
|
+
"model": "granite4.1:3b",
|
|
53
|
+
"category": "parallel",
|
|
54
|
+
"total": 200,
|
|
55
|
+
"rawCorrect": 166,
|
|
56
|
+
"betterCorrect": 166,
|
|
57
|
+
"errors": 0,
|
|
58
|
+
"repaired": 0
|
|
59
|
+
},
|
|
60
|
+
{
|
|
61
|
+
"model": "granite4.1:3b",
|
|
62
|
+
"category": "parallel_multiple",
|
|
63
|
+
"total": 200,
|
|
64
|
+
"rawCorrect": 157,
|
|
65
|
+
"betterCorrect": 157,
|
|
66
|
+
"errors": 0,
|
|
67
|
+
"repaired": 0
|
|
68
|
+
},
|
|
69
|
+
{
|
|
70
|
+
"model": "granite4.1:3b",
|
|
71
|
+
"category": "irrelevance",
|
|
72
|
+
"total": 240,
|
|
73
|
+
"rawCorrect": 161,
|
|
74
|
+
"betterCorrect": 240,
|
|
75
|
+
"errors": 0,
|
|
76
|
+
"repaired": 79
|
|
77
|
+
},
|
|
78
|
+
{
|
|
79
|
+
"model": "granite4.1:3b",
|
|
80
|
+
"category": "live_simple",
|
|
81
|
+
"total": 258,
|
|
82
|
+
"rawCorrect": 191,
|
|
83
|
+
"betterCorrect": 191,
|
|
84
|
+
"errors": 0,
|
|
85
|
+
"repaired": 0
|
|
86
|
+
},
|
|
87
|
+
{
|
|
88
|
+
"model": "granite4.1:3b",
|
|
89
|
+
"category": "live_multiple",
|
|
90
|
+
"total": 1053,
|
|
91
|
+
"rawCorrect": 746,
|
|
92
|
+
"betterCorrect": 748,
|
|
93
|
+
"errors": 0,
|
|
94
|
+
"repaired": 2
|
|
95
|
+
},
|
|
96
|
+
{
|
|
97
|
+
"model": "granite4.1:3b",
|
|
98
|
+
"category": "live_parallel",
|
|
99
|
+
"total": 16,
|
|
100
|
+
"rawCorrect": 11,
|
|
101
|
+
"betterCorrect": 11,
|
|
102
|
+
"errors": 0,
|
|
103
|
+
"repaired": 0
|
|
104
|
+
},
|
|
105
|
+
{
|
|
106
|
+
"model": "granite4.1:3b",
|
|
107
|
+
"category": "live_parallel_multiple",
|
|
108
|
+
"total": 24,
|
|
109
|
+
"rawCorrect": 17,
|
|
110
|
+
"betterCorrect": 17,
|
|
111
|
+
"errors": 0,
|
|
112
|
+
"repaired": 0
|
|
113
|
+
},
|
|
114
|
+
{
|
|
115
|
+
"model": "granite4.1:3b",
|
|
116
|
+
"category": "live_irrelevance",
|
|
117
|
+
"total": 884,
|
|
118
|
+
"rawCorrect": 579,
|
|
119
|
+
"betterCorrect": 875,
|
|
120
|
+
"errors": 7,
|
|
121
|
+
"repaired": 296
|
|
122
|
+
}
|
|
123
|
+
]
|
|
124
|
+
},
|
|
7
125
|
{
|
|
8
126
|
"model": "qwen3:0.6b",
|
|
9
127
|
"total": 3625,
|
|
@@ -240,6 +358,124 @@
|
|
|
240
358
|
}
|
|
241
359
|
]
|
|
242
360
|
},
|
|
361
|
+
{
|
|
362
|
+
"model": "qwen3.5:2b",
|
|
363
|
+
"total": 3625,
|
|
364
|
+
"rawCorrect": 1954,
|
|
365
|
+
"betterCorrect": 1990,
|
|
366
|
+
"errors": 1308,
|
|
367
|
+
"repaired": 55,
|
|
368
|
+
"categories": [
|
|
369
|
+
{
|
|
370
|
+
"model": "qwen3.5:2b",
|
|
371
|
+
"category": "simple_python",
|
|
372
|
+
"total": 400,
|
|
373
|
+
"rawCorrect": 118,
|
|
374
|
+
"betterCorrect": 130,
|
|
375
|
+
"errors": 256,
|
|
376
|
+
"repaired": 15
|
|
377
|
+
},
|
|
378
|
+
{
|
|
379
|
+
"model": "qwen3.5:2b",
|
|
380
|
+
"category": "simple_java",
|
|
381
|
+
"total": 100,
|
|
382
|
+
"rawCorrect": 14,
|
|
383
|
+
"betterCorrect": 17,
|
|
384
|
+
"errors": 81,
|
|
385
|
+
"repaired": 6
|
|
386
|
+
},
|
|
387
|
+
{
|
|
388
|
+
"model": "qwen3.5:2b",
|
|
389
|
+
"category": "simple_javascript",
|
|
390
|
+
"total": 50,
|
|
391
|
+
"rawCorrect": 1,
|
|
392
|
+
"betterCorrect": 1,
|
|
393
|
+
"errors": 48,
|
|
394
|
+
"repaired": 0
|
|
395
|
+
},
|
|
396
|
+
{
|
|
397
|
+
"model": "qwen3.5:2b",
|
|
398
|
+
"category": "multiple",
|
|
399
|
+
"total": 200,
|
|
400
|
+
"rawCorrect": 46,
|
|
401
|
+
"betterCorrect": 48,
|
|
402
|
+
"errors": 151,
|
|
403
|
+
"repaired": 2
|
|
404
|
+
},
|
|
405
|
+
{
|
|
406
|
+
"model": "qwen3.5:2b",
|
|
407
|
+
"category": "parallel",
|
|
408
|
+
"total": 200,
|
|
409
|
+
"rawCorrect": 36,
|
|
410
|
+
"betterCorrect": 36,
|
|
411
|
+
"errors": 157,
|
|
412
|
+
"repaired": 1
|
|
413
|
+
},
|
|
414
|
+
{
|
|
415
|
+
"model": "qwen3.5:2b",
|
|
416
|
+
"category": "parallel_multiple",
|
|
417
|
+
"total": 200,
|
|
418
|
+
"rawCorrect": 35,
|
|
419
|
+
"betterCorrect": 35,
|
|
420
|
+
"errors": 159,
|
|
421
|
+
"repaired": 0
|
|
422
|
+
},
|
|
423
|
+
{
|
|
424
|
+
"model": "qwen3.5:2b",
|
|
425
|
+
"category": "irrelevance",
|
|
426
|
+
"total": 240,
|
|
427
|
+
"rawCorrect": 167,
|
|
428
|
+
"betterCorrect": 174,
|
|
429
|
+
"errors": 66,
|
|
430
|
+
"repaired": 7
|
|
431
|
+
},
|
|
432
|
+
{
|
|
433
|
+
"model": "qwen3.5:2b",
|
|
434
|
+
"category": "live_simple",
|
|
435
|
+
"total": 258,
|
|
436
|
+
"rawCorrect": 155,
|
|
437
|
+
"betterCorrect": 161,
|
|
438
|
+
"errors": 41,
|
|
439
|
+
"repaired": 8
|
|
440
|
+
},
|
|
441
|
+
{
|
|
442
|
+
"model": "qwen3.5:2b",
|
|
443
|
+
"category": "live_multiple",
|
|
444
|
+
"total": 1053,
|
|
445
|
+
"rawCorrect": 720,
|
|
446
|
+
"betterCorrect": 721,
|
|
447
|
+
"errors": 110,
|
|
448
|
+
"repaired": 10
|
|
449
|
+
},
|
|
450
|
+
{
|
|
451
|
+
"model": "qwen3.5:2b",
|
|
452
|
+
"category": "live_parallel",
|
|
453
|
+
"total": 16,
|
|
454
|
+
"rawCorrect": 10,
|
|
455
|
+
"betterCorrect": 10,
|
|
456
|
+
"errors": 2,
|
|
457
|
+
"repaired": 0
|
|
458
|
+
},
|
|
459
|
+
{
|
|
460
|
+
"model": "qwen3.5:2b",
|
|
461
|
+
"category": "live_parallel_multiple",
|
|
462
|
+
"total": 24,
|
|
463
|
+
"rawCorrect": 12,
|
|
464
|
+
"betterCorrect": 11,
|
|
465
|
+
"errors": 6,
|
|
466
|
+
"repaired": 0
|
|
467
|
+
},
|
|
468
|
+
{
|
|
469
|
+
"model": "qwen3.5:2b",
|
|
470
|
+
"category": "live_irrelevance",
|
|
471
|
+
"total": 884,
|
|
472
|
+
"rawCorrect": 640,
|
|
473
|
+
"betterCorrect": 646,
|
|
474
|
+
"errors": 231,
|
|
475
|
+
"repaired": 6
|
|
476
|
+
}
|
|
477
|
+
]
|
|
478
|
+
},
|
|
243
479
|
{
|
|
244
480
|
"model": "lfm2.5-thinking:latest",
|
|
245
481
|
"total": 3625,
|
package/docs/banner.svg
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
<svg xmlns="http://www.w3.org/2000/svg" width="1400" height="520" viewBox="0 0 1400 520" role="img" aria-labelledby="title desc">
|
|
2
2
|
<title id="title">BetterCall banner</title>
|
|
3
|
-
<desc id="desc">BetterCall is a one-line wrapper with
|
|
3
|
+
<desc id="desc">BetterCall is a one-line wrapper with five full BFCL remote runs completed; the best run improves from 73.4 percent to 83.8 percent.</desc>
|
|
4
4
|
<defs>
|
|
5
5
|
<linearGradient id="background" x1="0" y1="0" x2="1" y2="1">
|
|
6
6
|
<stop offset="0" stop-color="#07111f"/>
|
|
@@ -24,6 +24,6 @@
|
|
|
24
24
|
<g transform="translate(112 112)">
|
|
25
25
|
<text x="0" y="80" font-family="Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, Segoe UI, sans-serif" font-size="78" font-weight="800" fill="#f8fbff">BetterCall</text>
|
|
26
26
|
<rect x="4" y="116" width="430" height="8" rx="4" fill="url(#accent)"/>
|
|
27
|
-
<text x="0" y="186" font-family="Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, Segoe UI, sans-serif" font-size="34" font-weight="670" fill="#dcecff">
|
|
27
|
+
<text x="0" y="186" font-family="Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, Segoe UI, sans-serif" font-size="34" font-weight="670" fill="#dcecff">Five full BFCL remote runs. Best: 73.4% → 83.8%.</text>
|
|
28
28
|
</g>
|
|
29
29
|
</svg>
|