rtr-bench 0.1.5 → 0.2.1
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 +166 -58
- package/data/splits/v1.json +184 -0
- package/dist/cli.js +1441 -56
- package/docs/development-pilot-2026-11-14.json +262 -0
- package/docs/distribution.md +102 -0
- package/docs/final-run-plan-8000.json +900 -0
- package/docs/final-run-plan-8000.md +73 -0
- package/docs/learn-room.md +188 -0
- package/docs/npm-release.md +37 -0
- package/docs/preflight-audit.md +81 -0
- package/docs/preflight-providers-2026-11-14.json +497 -0
- package/package.json +15 -3
- package/results/leaderboard-scatter.png +0 -0
- package/tests/fixtures/distribution-pilot.json +7 -0
- package/tests/fixtures/learn-room-four-strategies.json +58 -0
- package/tests/fixtures/learn-room-pilot.json +16 -0
|
@@ -0,0 +1,497 @@
|
|
|
1
|
+
{
|
|
2
|
+
"checkedOn": "2026-11-14",
|
|
3
|
+
"basis": "Public OpenRouter metadata only; no inference calls. Availability and prices may change.",
|
|
4
|
+
"modelsSource": "https://openrouter.ai/api/v1/models",
|
|
5
|
+
"selected": [
|
|
6
|
+
{
|
|
7
|
+
"model": "z-ai/glm-5.3",
|
|
8
|
+
"source": "https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints",
|
|
9
|
+
"selected": {
|
|
10
|
+
"tag": "wafer/us",
|
|
11
|
+
"status": 0,
|
|
12
|
+
"quantization": "fp4",
|
|
13
|
+
"context_length": 1048576,
|
|
14
|
+
"max_completion_tokens": 943718,
|
|
15
|
+
"supported_parameters": [
|
|
16
|
+
"reasoning",
|
|
17
|
+
"include_reasoning",
|
|
18
|
+
"temperature",
|
|
19
|
+
"top_p",
|
|
20
|
+
"top_k",
|
|
21
|
+
"min_p",
|
|
22
|
+
"frequency_penalty",
|
|
23
|
+
"presence_penalty",
|
|
24
|
+
"repetition_penalty",
|
|
25
|
+
"stop",
|
|
26
|
+
"seed",
|
|
27
|
+
"max_tokens",
|
|
28
|
+
"logit_bias",
|
|
29
|
+
"response_format",
|
|
30
|
+
"structured_outputs",
|
|
31
|
+
"tools",
|
|
32
|
+
"tool_choice",
|
|
33
|
+
"logprobs",
|
|
34
|
+
"top_logprobs",
|
|
35
|
+
"reasoning_effort"
|
|
36
|
+
],
|
|
37
|
+
"pricing": {
|
|
38
|
+
"prompt": "0.0000000699",
|
|
39
|
+
"completion": "0.0000014",
|
|
40
|
+
"input_cache_read": "0.0000000689",
|
|
41
|
+
"discount": 0
|
|
42
|
+
}
|
|
43
|
+
},
|
|
44
|
+
"reasoning": {
|
|
45
|
+
"mandatory": true,
|
|
46
|
+
"default_enabled": true,
|
|
47
|
+
"supported_efforts": [
|
|
48
|
+
"max",
|
|
49
|
+
"high",
|
|
50
|
+
"low"
|
|
51
|
+
],
|
|
52
|
+
"default_effort": "max"
|
|
53
|
+
}
|
|
54
|
+
},
|
|
55
|
+
{
|
|
56
|
+
"model": "minimax/minimax-m3.1-flash",
|
|
57
|
+
"source": "https://openrouter.ai/api/v1/models/minimax/minimax-m3.1-flash/endpoints",
|
|
58
|
+
"selected": {
|
|
59
|
+
"tag": "inferact-vllm/nvfp4",
|
|
60
|
+
"status": 0,
|
|
61
|
+
"quantization": "nvfp4",
|
|
62
|
+
"context_length": 1048576,
|
|
63
|
+
"max_completion_tokens": 131072,
|
|
64
|
+
"supported_parameters": [
|
|
65
|
+
"reasoning",
|
|
66
|
+
"include_reasoning",
|
|
67
|
+
"frequency_penalty",
|
|
68
|
+
"max_tokens",
|
|
69
|
+
"presence_penalty",
|
|
70
|
+
"repetition_penalty",
|
|
71
|
+
"seed",
|
|
72
|
+
"stop",
|
|
73
|
+
"temperature",
|
|
74
|
+
"top_k",
|
|
75
|
+
"top_p",
|
|
76
|
+
"tools",
|
|
77
|
+
"tool_choice",
|
|
78
|
+
"response_format",
|
|
79
|
+
"structured_outputs",
|
|
80
|
+
"logprobs",
|
|
81
|
+
"top_logprobs",
|
|
82
|
+
"reasoning_effort"
|
|
83
|
+
],
|
|
84
|
+
"pricing": {
|
|
85
|
+
"prompt": "0.000000075",
|
|
86
|
+
"completion": "0.0000003",
|
|
87
|
+
"input_cache_read": "0.0000000075",
|
|
88
|
+
"discount": 0
|
|
89
|
+
}
|
|
90
|
+
},
|
|
91
|
+
"reasoning": {
|
|
92
|
+
"mandatory": true,
|
|
93
|
+
"supported_efforts": [
|
|
94
|
+
"max",
|
|
95
|
+
"xhigh",
|
|
96
|
+
"high",
|
|
97
|
+
"medium",
|
|
98
|
+
"low"
|
|
99
|
+
],
|
|
100
|
+
"default_effort": "max"
|
|
101
|
+
}
|
|
102
|
+
},
|
|
103
|
+
{
|
|
104
|
+
"model": "xiaomi/mimo-v2.6-flash",
|
|
105
|
+
"source": "https://openrouter.ai/api/v1/models/xiaomi/mimo-v2.6-flash/endpoints",
|
|
106
|
+
"selected": {
|
|
107
|
+
"tag": "gmicloud/bf16",
|
|
108
|
+
"status": -2,
|
|
109
|
+
"quantization": "bf16",
|
|
110
|
+
"context_length": 1050000,
|
|
111
|
+
"max_completion_tokens": 945000,
|
|
112
|
+
"supported_parameters": [
|
|
113
|
+
"reasoning",
|
|
114
|
+
"include_reasoning",
|
|
115
|
+
"max_tokens",
|
|
116
|
+
"temperature",
|
|
117
|
+
"top_p",
|
|
118
|
+
"seed",
|
|
119
|
+
"response_format",
|
|
120
|
+
"structured_outputs",
|
|
121
|
+
"tools",
|
|
122
|
+
"tool_choice"
|
|
123
|
+
],
|
|
124
|
+
"pricing": {
|
|
125
|
+
"prompt": "0.000000112",
|
|
126
|
+
"completion": "0.000000224",
|
|
127
|
+
"input_cache_read": "0.0000000024",
|
|
128
|
+
"discount": 0.2
|
|
129
|
+
}
|
|
130
|
+
},
|
|
131
|
+
"reasoning": {
|
|
132
|
+
"mandatory": false
|
|
133
|
+
},
|
|
134
|
+
"candidateReplacement": {
|
|
135
|
+
"tag": "xiaomi/fp8",
|
|
136
|
+
"status": 0,
|
|
137
|
+
"quantization": "fp8",
|
|
138
|
+
"context_length": 1048576,
|
|
139
|
+
"max_completion_tokens": 131072,
|
|
140
|
+
"supported_parameters": [
|
|
141
|
+
"reasoning",
|
|
142
|
+
"include_reasoning",
|
|
143
|
+
"max_tokens",
|
|
144
|
+
"temperature",
|
|
145
|
+
"top_p",
|
|
146
|
+
"stop",
|
|
147
|
+
"response_format",
|
|
148
|
+
"tools",
|
|
149
|
+
"tool_choice",
|
|
150
|
+
"frequency_penalty",
|
|
151
|
+
"presence_penalty",
|
|
152
|
+
"structured_outputs"
|
|
153
|
+
],
|
|
154
|
+
"pricing": {
|
|
155
|
+
"prompt": "0.00000014",
|
|
156
|
+
"completion": "0.00000028",
|
|
157
|
+
"input_cache_read": "0.0000000028",
|
|
158
|
+
"discount": 0
|
|
159
|
+
}
|
|
160
|
+
}
|
|
161
|
+
},
|
|
162
|
+
{
|
|
163
|
+
"model": "deepseek/deepseek-v4.1-flash-1017",
|
|
164
|
+
"source": "https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash-1017/endpoints",
|
|
165
|
+
"selected": {
|
|
166
|
+
"tag": "sail-research/fp4/us",
|
|
167
|
+
"status": 0,
|
|
168
|
+
"quantization": "fp4",
|
|
169
|
+
"context_length": 1048576,
|
|
170
|
+
"max_completion_tokens": 384000,
|
|
171
|
+
"supported_parameters": [
|
|
172
|
+
"reasoning",
|
|
173
|
+
"include_reasoning",
|
|
174
|
+
"frequency_penalty",
|
|
175
|
+
"max_tokens",
|
|
176
|
+
"presence_penalty",
|
|
177
|
+
"seed",
|
|
178
|
+
"stop",
|
|
179
|
+
"temperature",
|
|
180
|
+
"top_k",
|
|
181
|
+
"top_p",
|
|
182
|
+
"response_format",
|
|
183
|
+
"structured_outputs",
|
|
184
|
+
"tools",
|
|
185
|
+
"tool_choice",
|
|
186
|
+
"logprobs",
|
|
187
|
+
"top_logprobs",
|
|
188
|
+
"reasoning_effort"
|
|
189
|
+
],
|
|
190
|
+
"pricing": {
|
|
191
|
+
"prompt": "0.00000007272",
|
|
192
|
+
"completion": "0.000000108",
|
|
193
|
+
"input_cache_read": "0.000000007",
|
|
194
|
+
"discount": 0
|
|
195
|
+
}
|
|
196
|
+
},
|
|
197
|
+
"reasoning": {
|
|
198
|
+
"mandatory": false,
|
|
199
|
+
"default_enabled": true,
|
|
200
|
+
"supported_efforts": [
|
|
201
|
+
"max",
|
|
202
|
+
"high",
|
|
203
|
+
"low",
|
|
204
|
+
"none"
|
|
205
|
+
],
|
|
206
|
+
"default_effort": "high"
|
|
207
|
+
}
|
|
208
|
+
},
|
|
209
|
+
{
|
|
210
|
+
"model": "tencent/hy3",
|
|
211
|
+
"source": "https://openrouter.ai/api/v1/models/tencent/hy3/endpoints",
|
|
212
|
+
"selected": {
|
|
213
|
+
"tag": "gmicloud/bf16",
|
|
214
|
+
"status": 0,
|
|
215
|
+
"quantization": "bf16",
|
|
216
|
+
"context_length": 262144,
|
|
217
|
+
"max_completion_tokens": 235929,
|
|
218
|
+
"supported_parameters": [
|
|
219
|
+
"reasoning",
|
|
220
|
+
"include_reasoning",
|
|
221
|
+
"max_tokens",
|
|
222
|
+
"temperature",
|
|
223
|
+
"top_p",
|
|
224
|
+
"seed",
|
|
225
|
+
"response_format",
|
|
226
|
+
"tools",
|
|
227
|
+
"tool_choice",
|
|
228
|
+
"reasoning_effort"
|
|
229
|
+
],
|
|
230
|
+
"pricing": {
|
|
231
|
+
"prompt": "0.00000014",
|
|
232
|
+
"completion": "0.00000058",
|
|
233
|
+
"input_cache_read": "0.000000035",
|
|
234
|
+
"discount": 0
|
|
235
|
+
}
|
|
236
|
+
},
|
|
237
|
+
"reasoning": {
|
|
238
|
+
"mandatory": false,
|
|
239
|
+
"default_enabled": true,
|
|
240
|
+
"supported_efforts": [
|
|
241
|
+
"high",
|
|
242
|
+
"low",
|
|
243
|
+
"none"
|
|
244
|
+
],
|
|
245
|
+
"default_effort": "high"
|
|
246
|
+
}
|
|
247
|
+
},
|
|
248
|
+
{
|
|
249
|
+
"model": "google/gemini-3.8-flash",
|
|
250
|
+
"source": "https://openrouter.ai/api/v1/models/google/gemini-3.8-flash/endpoints",
|
|
251
|
+
"selected": {
|
|
252
|
+
"tag": "google-ai-studio",
|
|
253
|
+
"status": 0,
|
|
254
|
+
"quantization": "unknown",
|
|
255
|
+
"context_length": 1048576,
|
|
256
|
+
"max_completion_tokens": 65536,
|
|
257
|
+
"supported_parameters": [
|
|
258
|
+
"reasoning",
|
|
259
|
+
"include_reasoning",
|
|
260
|
+
"max_tokens",
|
|
261
|
+
"temperature",
|
|
262
|
+
"top_p",
|
|
263
|
+
"seed",
|
|
264
|
+
"response_format",
|
|
265
|
+
"structured_outputs",
|
|
266
|
+
"tool_choice",
|
|
267
|
+
"tools",
|
|
268
|
+
"reasoning_effort"
|
|
269
|
+
],
|
|
270
|
+
"pricing": {
|
|
271
|
+
"prompt": "0.00000075",
|
|
272
|
+
"completion": "0.00000375",
|
|
273
|
+
"image": "0.00000075",
|
|
274
|
+
"audio": "0.00000075",
|
|
275
|
+
"input_audio_cache": "0.000000075",
|
|
276
|
+
"web_search": "0.014",
|
|
277
|
+
"internal_reasoning": "0.00000375",
|
|
278
|
+
"input_cache_read": "0.000000075",
|
|
279
|
+
"input_cache_write": "0.0000000416666666666667",
|
|
280
|
+
"discount": 0.5
|
|
281
|
+
}
|
|
282
|
+
},
|
|
283
|
+
"reasoning": {
|
|
284
|
+
"mandatory": true,
|
|
285
|
+
"default_enabled": true,
|
|
286
|
+
"supported_efforts": [
|
|
287
|
+
"high",
|
|
288
|
+
"medium",
|
|
289
|
+
"low"
|
|
290
|
+
],
|
|
291
|
+
"default_effort": "medium"
|
|
292
|
+
}
|
|
293
|
+
},
|
|
294
|
+
{
|
|
295
|
+
"model": "openai/gpt-6-luna",
|
|
296
|
+
"source": "https://openrouter.ai/api/v1/models/openai/gpt-6-luna/endpoints",
|
|
297
|
+
"selected": {
|
|
298
|
+
"tag": "openai",
|
|
299
|
+
"status": 0,
|
|
300
|
+
"quantization": "unknown",
|
|
301
|
+
"context_length": 1050000,
|
|
302
|
+
"max_completion_tokens": 128000,
|
|
303
|
+
"supported_parameters": [
|
|
304
|
+
"reasoning",
|
|
305
|
+
"include_reasoning",
|
|
306
|
+
"seed",
|
|
307
|
+
"max_tokens",
|
|
308
|
+
"response_format",
|
|
309
|
+
"structured_outputs",
|
|
310
|
+
"tools",
|
|
311
|
+
"tool_choice",
|
|
312
|
+
"verbosity",
|
|
313
|
+
"reasoning_effort"
|
|
314
|
+
],
|
|
315
|
+
"pricing": {
|
|
316
|
+
"prompt": "0.0000001",
|
|
317
|
+
"completion": "0.0000005",
|
|
318
|
+
"web_search": "0.01",
|
|
319
|
+
"input_cache_read": "0.00000001",
|
|
320
|
+
"input_cache_write": "0.000000125",
|
|
321
|
+
"discount": 0,
|
|
322
|
+
"overrides": [
|
|
323
|
+
{
|
|
324
|
+
"min_prompt_tokens": 272000,
|
|
325
|
+
"prompt": "0.0000002",
|
|
326
|
+
"completion": "0.00000075",
|
|
327
|
+
"input_cache_read": "0.00000002",
|
|
328
|
+
"input_cache_write": "0.00000025"
|
|
329
|
+
}
|
|
330
|
+
]
|
|
331
|
+
}
|
|
332
|
+
},
|
|
333
|
+
"reasoning": {
|
|
334
|
+
"mandatory": false,
|
|
335
|
+
"default_enabled": true,
|
|
336
|
+
"supported_efforts": [
|
|
337
|
+
"max",
|
|
338
|
+
"xhigh",
|
|
339
|
+
"high",
|
|
340
|
+
"medium",
|
|
341
|
+
"low",
|
|
342
|
+
"none"
|
|
343
|
+
],
|
|
344
|
+
"default_effort": "medium"
|
|
345
|
+
}
|
|
346
|
+
},
|
|
347
|
+
{
|
|
348
|
+
"model": "anthropic/claude-haiku-5.5",
|
|
349
|
+
"source": "https://openrouter.ai/api/v1/models/anthropic/claude-haiku-5.5/endpoints",
|
|
350
|
+
"selected": {
|
|
351
|
+
"tag": "anthropic",
|
|
352
|
+
"status": 0,
|
|
353
|
+
"quantization": "unknown",
|
|
354
|
+
"context_length": 1000000,
|
|
355
|
+
"max_completion_tokens": 128000,
|
|
356
|
+
"supported_parameters": [
|
|
357
|
+
"reasoning",
|
|
358
|
+
"include_reasoning",
|
|
359
|
+
"max_tokens",
|
|
360
|
+
"stop",
|
|
361
|
+
"tools",
|
|
362
|
+
"tool_choice",
|
|
363
|
+
"structured_outputs",
|
|
364
|
+
"response_format",
|
|
365
|
+
"verbosity",
|
|
366
|
+
"reasoning_effort"
|
|
367
|
+
],
|
|
368
|
+
"pricing": {
|
|
369
|
+
"prompt": "0.0000001",
|
|
370
|
+
"completion": "0.0000005",
|
|
371
|
+
"web_search": "0.01",
|
|
372
|
+
"input_cache_read": "0.00000001",
|
|
373
|
+
"input_cache_write": "0.000000125",
|
|
374
|
+
"input_cache_write_1h": "0.0000002",
|
|
375
|
+
"discount": 0,
|
|
376
|
+
"overrides": [
|
|
377
|
+
{
|
|
378
|
+
"min_prompt_tokens": 100000,
|
|
379
|
+
"prompt": "0.0000005",
|
|
380
|
+
"completion": "0.0000025",
|
|
381
|
+
"input_cache_read": "0.00000005",
|
|
382
|
+
"input_cache_write": "0.000000625",
|
|
383
|
+
"input_cache_write_1h": "0.000001"
|
|
384
|
+
}
|
|
385
|
+
]
|
|
386
|
+
}
|
|
387
|
+
},
|
|
388
|
+
"reasoning": {
|
|
389
|
+
"mandatory": false,
|
|
390
|
+
"supported_efforts": [
|
|
391
|
+
"max",
|
|
392
|
+
"xhigh",
|
|
393
|
+
"high",
|
|
394
|
+
"medium",
|
|
395
|
+
"low",
|
|
396
|
+
"none"
|
|
397
|
+
],
|
|
398
|
+
"default_effort": "medium"
|
|
399
|
+
}
|
|
400
|
+
},
|
|
401
|
+
{
|
|
402
|
+
"model": "thinkingmachines/inkling-small",
|
|
403
|
+
"source": "https://openrouter.ai/api/v1/models/thinkingmachines/inkling-small/endpoints",
|
|
404
|
+
"selected": {
|
|
405
|
+
"tag": "deepinfra/fp4",
|
|
406
|
+
"status": 0,
|
|
407
|
+
"quantization": "fp4",
|
|
408
|
+
"context_length": 524288,
|
|
409
|
+
"max_completion_tokens": 262144,
|
|
410
|
+
"supported_parameters": [
|
|
411
|
+
"reasoning",
|
|
412
|
+
"include_reasoning",
|
|
413
|
+
"max_tokens",
|
|
414
|
+
"temperature",
|
|
415
|
+
"top_p",
|
|
416
|
+
"stop",
|
|
417
|
+
"frequency_penalty",
|
|
418
|
+
"presence_penalty",
|
|
419
|
+
"repetition_penalty",
|
|
420
|
+
"top_k",
|
|
421
|
+
"seed",
|
|
422
|
+
"min_p",
|
|
423
|
+
"tools",
|
|
424
|
+
"tool_choice",
|
|
425
|
+
"logit_bias",
|
|
426
|
+
"reasoning_effort"
|
|
427
|
+
],
|
|
428
|
+
"pricing": {
|
|
429
|
+
"prompt": "0.00000045",
|
|
430
|
+
"completion": "0.0000012",
|
|
431
|
+
"input_cache_read": "0.0000001",
|
|
432
|
+
"discount": 0
|
|
433
|
+
}
|
|
434
|
+
},
|
|
435
|
+
"reasoning": {
|
|
436
|
+
"mandatory": false,
|
|
437
|
+
"default_enabled": true,
|
|
438
|
+
"supported_efforts": [
|
|
439
|
+
"max",
|
|
440
|
+
"high",
|
|
441
|
+
"medium",
|
|
442
|
+
"low",
|
|
443
|
+
"minimal",
|
|
444
|
+
"none"
|
|
445
|
+
],
|
|
446
|
+
"default_effort": "high"
|
|
447
|
+
}
|
|
448
|
+
},
|
|
449
|
+
{
|
|
450
|
+
"model": "openai/gpt-oss-120b",
|
|
451
|
+
"source": "https://openrouter.ai/api/v1/models/openai/gpt-oss-120b/endpoints",
|
|
452
|
+
"selected": {
|
|
453
|
+
"tag": "primeintellect/fp4",
|
|
454
|
+
"status": 0,
|
|
455
|
+
"quantization": "fp4",
|
|
456
|
+
"context_length": 131072,
|
|
457
|
+
"max_completion_tokens": 65536,
|
|
458
|
+
"supported_parameters": [
|
|
459
|
+
"reasoning",
|
|
460
|
+
"include_reasoning",
|
|
461
|
+
"frequency_penalty",
|
|
462
|
+
"logit_bias",
|
|
463
|
+
"max_tokens",
|
|
464
|
+
"min_p",
|
|
465
|
+
"presence_penalty",
|
|
466
|
+
"repetition_penalty",
|
|
467
|
+
"seed",
|
|
468
|
+
"stop",
|
|
469
|
+
"temperature",
|
|
470
|
+
"top_a",
|
|
471
|
+
"top_k",
|
|
472
|
+
"top_p",
|
|
473
|
+
"tools",
|
|
474
|
+
"response_format",
|
|
475
|
+
"structured_outputs",
|
|
476
|
+
"tool_choice",
|
|
477
|
+
"reasoning_effort"
|
|
478
|
+
],
|
|
479
|
+
"pricing": {
|
|
480
|
+
"prompt": "0.000000035",
|
|
481
|
+
"completion": "0.000000075",
|
|
482
|
+
"input_cache_read": "0.000000031",
|
|
483
|
+
"discount": 0
|
|
484
|
+
}
|
|
485
|
+
},
|
|
486
|
+
"reasoning": {
|
|
487
|
+
"mandatory": true,
|
|
488
|
+
"supported_efforts": [
|
|
489
|
+
"high",
|
|
490
|
+
"medium",
|
|
491
|
+
"low"
|
|
492
|
+
],
|
|
493
|
+
"default_effort": "medium"
|
|
494
|
+
}
|
|
495
|
+
}
|
|
496
|
+
]
|
|
497
|
+
}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "rtr-bench",
|
|
3
|
-
"version": "0.1
|
|
3
|
+
"version": "0.2.1",
|
|
4
4
|
"description": "Can a language model predict how a crowd reads a word? A cultural fluency benchmark built from Mixed Messages.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "MIT",
|
|
@@ -17,7 +17,7 @@
|
|
|
17
17
|
"generative-art"
|
|
18
18
|
],
|
|
19
19
|
"engines": {
|
|
20
|
-
"node": ">=18"
|
|
20
|
+
"node": ">=22.18.0"
|
|
21
21
|
},
|
|
22
22
|
"bin": {
|
|
23
23
|
"rtr-bench": "dist/cli.js"
|
|
@@ -25,11 +25,23 @@
|
|
|
25
25
|
"files": [
|
|
26
26
|
"dist/",
|
|
27
27
|
"data/",
|
|
28
|
+
"docs/distribution.md",
|
|
29
|
+
"docs/learn-room.md",
|
|
30
|
+
"docs/npm-release.md",
|
|
31
|
+
"docs/preflight-audit.md",
|
|
32
|
+
"docs/preflight-providers-2026-11-14.json",
|
|
33
|
+
"tests/fixtures/distribution-pilot.json",
|
|
34
|
+
"tests/fixtures/learn-room-pilot.json",
|
|
35
|
+
"tests/fixtures/learn-room-four-strategies.json",
|
|
28
36
|
"results/leaderboard-scatter.png",
|
|
29
37
|
"README.md",
|
|
30
|
-
"LICENSE"
|
|
38
|
+
"LICENSE",
|
|
39
|
+
"docs/development-pilot-2026-11-14.json",
|
|
40
|
+
"docs/final-run-plan-8000.md",
|
|
41
|
+
"docs/final-run-plan-8000.json"
|
|
31
42
|
],
|
|
32
43
|
"scripts": {
|
|
44
|
+
"test": "node --test tests/*.test.ts tests/distribution/*.test.ts tests/learn-room/*.test.ts",
|
|
33
45
|
"build": "esbuild src/cli.ts --bundle --platform=node --format=esm --outfile=dist/cli.js --external:node:*",
|
|
34
46
|
"prepack": "npm run build",
|
|
35
47
|
"export": "node scripts/export.mjs",
|
|
Binary file
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
{
|
|
2
|
+
"100": "{\"performed+uniting\": 0.2, \"honest+uniting\": 0.3, \"performed+dividing\": 0.4, \"honest+dividing\": 0.1}",
|
|
3
|
+
"101": "{\"performed+uniting\": 0.1, \"honest+uniting\": 0.2, \"performed+dividing\": 0.3, \"honest+dividing\": 0.4}",
|
|
4
|
+
"102": "{\"performed+uniting\": 0.25, \"honest+uniting\": 0.25, \"performed+dividing\": 0.25, \"honest+dividing\": 0.25}",
|
|
5
|
+
"103": "{\"performed+uniting\": 0.2, \"honest+uniting\": 0.2, \"performed+dividing\": 0.2, \"honest+dividing\": 0.2}",
|
|
6
|
+
"104": ""
|
|
7
|
+
}
|
|
@@ -0,0 +1,58 @@
|
|
|
1
|
+
{
|
|
2
|
+
"none": {
|
|
3
|
+
"100": "{\"performed+uniting\": 0.2, \"honest+uniting\": 0.3, \"performed+dividing\": 0.4, \"honest+dividing\": 0.1}",
|
|
4
|
+
"101": "{\"performed+uniting\": 0.1, \"honest+uniting\": 0.2, \"performed+dividing\": 0.3, \"honest+dividing\": 0.4}",
|
|
5
|
+
"102": "{\"performed+uniting\": 0.25, \"honest+uniting\": 0.25, \"performed+dividing\": 0.25, \"honest+dividing\": 0.25}",
|
|
6
|
+
"103": "{\"performed+uniting\": 0.2, \"honest+uniting\": 0.2, \"performed+dividing\": 0.2, \"honest+dividing\": 0.2}",
|
|
7
|
+
"104": ""
|
|
8
|
+
},
|
|
9
|
+
"random": {
|
|
10
|
+
"100": "{\"performed+uniting\": 0.35, \"honest+uniting\": 0.15, \"performed+dividing\": 0.35, \"honest+dividing\": 0.15}",
|
|
11
|
+
"101": "{\"performed+uniting\": 0.1, \"honest+uniting\": 0.2, \"performed+dividing\": 0.3, \"honest+dividing\": 0.4}",
|
|
12
|
+
"102": "{\"performed+uniting\": 0.25, \"honest+uniting\": 0.25, \"performed+dividing\": 0.25, \"honest+dividing\": 0.25}",
|
|
13
|
+
"103": "{\"performed+uniting\": 0.1, \"honest+uniting\": 0.6, \"performed+dividing\": 0.1, \"honest+dividing\": 0.2}",
|
|
14
|
+
"104": ""
|
|
15
|
+
},
|
|
16
|
+
"similar": {
|
|
17
|
+
"100": "{\"performed+uniting\": 0.35, \"honest+uniting\": 0.15, \"performed+dividing\": 0.35, \"honest+dividing\": 0.15}",
|
|
18
|
+
"101": "{\"performed+uniting\": 0.1, \"honest+uniting\": 0.2, \"performed+dividing\": 0.3, \"honest+dividing\": 0.4}",
|
|
19
|
+
"102": "{\"performed+uniting\": 0.25, \"honest+uniting\": 0.25, \"performed+dividing\": 0.25, \"honest+dividing\": 0.25}",
|
|
20
|
+
"103": "{\"performed+uniting\": 0.1, \"honest+uniting\": 0.6, \"performed+dividing\": 0.1, \"honest+dividing\": 0.2}",
|
|
21
|
+
"104": ""
|
|
22
|
+
},
|
|
23
|
+
"agent": {
|
|
24
|
+
"100": [
|
|
25
|
+
"{\"type\": \"list_examples\"}",
|
|
26
|
+
"{\"type\": \"inspect_example\", \"id\": 80}",
|
|
27
|
+
"{\"type\": \"submit_prediction\", \"prediction\": {\"performed+uniting\": 0.25, \"honest+uniting\": 0.25, \"performed+dividing\": 0.25, \"honest+dividing\": 0.25}}"
|
|
28
|
+
],
|
|
29
|
+
"101": [
|
|
30
|
+
"{\"type\": \"submit_prediction\", \"prediction\": {\"performed+uniting\": 0.25, \"honest+uniting\": 0.25, \"performed+dividing\": 0.25, \"honest+dividing\": 0.25}}"
|
|
31
|
+
],
|
|
32
|
+
"102": [
|
|
33
|
+
"bad json",
|
|
34
|
+
"{\"type\": \"list_examples\"}",
|
|
35
|
+
"{\"type\": \"inspect_example\", \"id\": 24}",
|
|
36
|
+
"{\"type\": \"inspect_example\", \"id\": 30}",
|
|
37
|
+
"{\"type\": \"inspect_example\", \"id\": 35}",
|
|
38
|
+
"{\"type\": \"inspect_example\", \"id\": 36}",
|
|
39
|
+
"{\"type\": \"submit_prediction\", \"prediction\": {\"performed+uniting\": 0.25, \"honest+uniting\": 0.25, \"performed+dividing\": 0.25, \"honest+dividing\": 0.25}}"
|
|
40
|
+
],
|
|
41
|
+
"103": [
|
|
42
|
+
"{\"type\": \"list_examples\"}",
|
|
43
|
+
"{\"type\": \"list_examples\"}",
|
|
44
|
+
"{\"type\": \"list_examples\"}",
|
|
45
|
+
"{\"type\": \"list_examples\"}",
|
|
46
|
+
"{\"type\": \"list_examples\"}",
|
|
47
|
+
"{\"type\": \"list_examples\"}",
|
|
48
|
+
"{\"type\": \"list_examples\"}",
|
|
49
|
+
"{\"type\": \"list_examples\"}"
|
|
50
|
+
],
|
|
51
|
+
"104": [
|
|
52
|
+
"{\"type\": \"list_examples\"}",
|
|
53
|
+
"{\"type\": \"inspect_example\", \"id\": 1}",
|
|
54
|
+
"{\"type\": \"inspect_example\", \"id\": 1}",
|
|
55
|
+
"{\"type\": \"submit_prediction\", \"prediction\": {}}"
|
|
56
|
+
]
|
|
57
|
+
}
|
|
58
|
+
}
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
{
|
|
2
|
+
"none": {
|
|
3
|
+
"100": "{\"performed+uniting\": 0.2, \"honest+uniting\": 0.3, \"performed+dividing\": 0.4, \"honest+dividing\": 0.1}",
|
|
4
|
+
"101": "{\"performed+uniting\": 0.1, \"honest+uniting\": 0.2, \"performed+dividing\": 0.3, \"honest+dividing\": 0.4}",
|
|
5
|
+
"102": "{\"performed+uniting\": 0.25, \"honest+uniting\": 0.25, \"performed+dividing\": 0.25, \"honest+dividing\": 0.25}",
|
|
6
|
+
"103": "{\"performed+uniting\": 0.2, \"honest+uniting\": 0.2, \"performed+dividing\": 0.2, \"honest+dividing\": 0.2}",
|
|
7
|
+
"104": ""
|
|
8
|
+
},
|
|
9
|
+
"random": {
|
|
10
|
+
"100": "{\"performed+uniting\": 0.35, \"honest+uniting\": 0.15, \"performed+dividing\": 0.35, \"honest+dividing\": 0.15}",
|
|
11
|
+
"101": "{\"performed+uniting\": 0.1, \"honest+uniting\": 0.2, \"performed+dividing\": 0.3, \"honest+dividing\": 0.4}",
|
|
12
|
+
"102": "{\"performed+uniting\": 0.25, \"honest+uniting\": 0.25, \"performed+dividing\": 0.25, \"honest+dividing\": 0.25}",
|
|
13
|
+
"103": "{\"performed+uniting\": 0.1, \"honest+uniting\": 0.6, \"performed+dividing\": 0.1, \"honest+dividing\": 0.2}",
|
|
14
|
+
"104": ""
|
|
15
|
+
}
|
|
16
|
+
}
|