modelspec-dev 0.1.0__py3-none-any.whl

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.
Files changed (63) hide show
  1. api/__init__.py +0 -0
  2. api/class_fit.py +334 -0
  3. api/classes.py +557 -0
  4. api/ranking/__init__.py +12 -0
  5. api/ranking/engine.py +1943 -0
  6. cli/__init__.py +0 -0
  7. cli/modelspec/__init__.py +0 -0
  8. cli/modelspec/cli.py +1819 -0
  9. cli/modelspec/commands/__init__.py +0 -0
  10. cli/modelspec/decide_cmd.py +333 -0
  11. cli/modelspec/offline.py +623 -0
  12. cli/modelspec/snapshot.py +698 -0
  13. cli/modelspec/snapshot_build_cmd.py +49 -0
  14. cli/modelspec/verify_cmd.py +125 -0
  15. cli/modelspec/vocab_cmd.py +204 -0
  16. cli/modelspec/vocabulary_cache.py +54 -0
  17. decision/__init__.py +13 -0
  18. decision/capability.py +872 -0
  19. decision/computed.py +125 -0
  20. decision/contract.py +1575 -0
  21. decision/engine.py +238 -0
  22. decision/excluded.py +34 -0
  23. decision/explain.py +908 -0
  24. decision/filter.py +796 -0
  25. decision/model.py +438 -0
  26. decision/normalise.py +604 -0
  27. decision/optimise.py +320 -0
  28. decision/registry.py +717 -0
  29. decision/relax.py +132 -0
  30. decision/resolve.py +111 -0
  31. decision/schema.py +21 -0
  32. decision/snapshot.py +1483 -0
  33. decision/sources.py +544 -0
  34. decision/templates.py +134 -0
  35. decision/verify.py +1745 -0
  36. decision/vocabulary.py +433 -0
  37. modelspec_dev-0.1.0.dist-info/METADATA +101 -0
  38. modelspec_dev-0.1.0.dist-info/RECORD +63 -0
  39. modelspec_dev-0.1.0.dist-info/WHEEL +4 -0
  40. modelspec_dev-0.1.0.dist-info/entry_points.txt +2 -0
  41. modelspec_dev-0.1.0.dist-info/licenses/LICENSE +43 -0
  42. modelspec_dev-0.1.0.dist-info/licenses/LICENSE-DATA +428 -0
  43. pipeline/__init__.py +0 -0
  44. pipeline/class_export.py +172 -0
  45. pipeline/hardware.py +434 -0
  46. pipeline/hosts.py +247 -0
  47. pipeline/load.py +224 -0
  48. pipeline/ranking.py +551 -0
  49. registry/domains.yaml +130 -0
  50. registry/facets.yaml +888 -0
  51. registry/harnesses.yaml +79 -0
  52. registry/providers.yaml +354 -0
  53. registry/sources.yaml +3059 -0
  54. registry/templates.yaml +166 -0
  55. schema/__init__.py +0 -0
  56. schema/applicability.py +147 -0
  57. schema/benchmark.py +175 -0
  58. schema/benchmark_eligibility.py +304 -0
  59. schema/card.py +1463 -0
  60. schema/enrichment.py +162 -0
  61. schema/enums.py +327 -0
  62. schema/graph.py +406 -0
  63. schema/suppliers.py +72 -0
registry/sources.yaml ADDED
@@ -0,0 +1,3059 @@
1
+ schema_version: 1
2
+ sources:
3
+ - id: anthropic-pricing
4
+ url: https://platform.claude.com/docs/en/about-claude/pricing
5
+ fetch: conditional_http
6
+ normaliser: html-default
7
+ cited_regions:
8
+ - id: page
9
+ locator:
10
+ kind: page
11
+ value: ''
12
+ - id: base-pricing
13
+ locator:
14
+ kind: table
15
+ value: '0'
16
+ - id: cache-multipliers
17
+ locator:
18
+ kind: table
19
+ value: '3'
20
+ - id: batch-pricing
21
+ locator:
22
+ kind: table
23
+ value: '5'
24
+ - id: anthropic-retention
25
+ url: https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data
26
+ fetch: conditional_http
27
+ normaliser: html-default
28
+ cited_regions:
29
+ - id: page
30
+ locator:
31
+ kind: page
32
+ value: ''
33
+ - id: anthropic-training
34
+ url: https://privacy.claude.com/en/articles/7996868-is-my-data-used-for-model-training
35
+ fetch: conditional_http
36
+ normaliser: html-default
37
+ cited_regions:
38
+ - id: page
39
+ locator:
40
+ kind: page
41
+ value: ''
42
+ - id: anthropic-zdr
43
+ url: https://privacy.claude.com/en/articles/8956058-i-have-a-zero-data-retention-agreement-with-anthropic-what-products-does-it-apply-to
44
+ fetch: conditional_http
45
+ normaliser: html-default
46
+ cited_regions:
47
+ - id: page
48
+ locator:
49
+ kind: page
50
+ value: ''
51
+ - id: anthropic-attestations
52
+ url: https://privacy.claude.com/en/articles/10015870-what-certifications-has-anthropic-obtained
53
+ fetch: conditional_http
54
+ normaliser: html-default
55
+ cited_regions:
56
+ - id: page
57
+ locator:
58
+ kind: page
59
+ value: ''
60
+ - id: aws-pricing
61
+ url: https://aws.amazon.com/bedrock/pricing/
62
+ fetch: rendered
63
+ normaliser: html-default
64
+ cited_regions:
65
+ - id: page
66
+ locator:
67
+ kind: page
68
+ value: ''
69
+ - id: global-cross-region-anthropic
70
+ locator:
71
+ kind: table
72
+ value: '26'
73
+ - id: aws-retention
74
+ url: https://docs.aws.amazon.com/bedrock/latest/userguide/data-retention.html
75
+ fetch: conditional_http
76
+ normaliser: html-default
77
+ cited_regions:
78
+ - id: page
79
+ locator:
80
+ kind: page
81
+ value: ''
82
+ - id: aws-training
83
+ url: https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/omni-opting-out-of-using-your-data-for-service-improvement.html
84
+ fetch: conditional_http
85
+ normaliser: html-default
86
+ cited_regions:
87
+ - id: page
88
+ locator:
89
+ kind: page
90
+ value: ''
91
+ - id: aws-attestations
92
+ url: https://aws.amazon.com/bedrock/security-compliance/
93
+ fetch: conditional_http
94
+ normaliser: html-default
95
+ cited_regions:
96
+ - id: page
97
+ locator:
98
+ kind: page
99
+ value: ''
100
+ - id: vertex-pricing
101
+ url: https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
102
+ fetch: conditional_http
103
+ normaliser: html-default
104
+ cited_regions:
105
+ - id: page
106
+ locator:
107
+ kind: page
108
+ value: ''
109
+ - id: gemini-standard
110
+ locator:
111
+ kind: table
112
+ value: '0'
113
+ - id: gemini-batch
114
+ locator:
115
+ kind: table
116
+ value: '2'
117
+ - id: partner-anthropic-regional
118
+ locator:
119
+ kind: table
120
+ value: '38'
121
+ - id: vertex-data
122
+ url: https://docs.cloud.google.com/vertex-ai/generative-ai/docs/vertex-ai-zero-data-retention
123
+ fetch: conditional_http
124
+ normaliser: html-default
125
+ cited_regions:
126
+ - id: page
127
+ locator:
128
+ kind: page
129
+ value: ''
130
+ - id: google-attestations
131
+ url: https://cloud.google.com/security/compliance/hipaa-compliance
132
+ fetch: conditional_http
133
+ normaliser: html-default
134
+ cited_regions:
135
+ - id: page
136
+ locator:
137
+ kind: page
138
+ value: ''
139
+ - id: azure-pricing
140
+ url: https://azure.microsoft.com/en-us/pricing/details/azure-openai/
141
+ fetch: rendered
142
+ normaliser: html-default
143
+ cited_regions:
144
+ - id: page
145
+ locator:
146
+ kind: page
147
+ value: ''
148
+ - id: gpt-6-pricing
149
+ locator:
150
+ kind: table
151
+ value: '1'
152
+ - id: gpt-5-6-pricing
153
+ locator:
154
+ kind: table
155
+ value: '2'
156
+ - id: gpt-5-4-pricing
157
+ locator:
158
+ kind: table
159
+ value: '4'
160
+ - id: azure-data
161
+ url: https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/data-privacy
162
+ fetch: conditional_http
163
+ normaliser: html-default
164
+ cited_regions:
165
+ - id: page
166
+ locator:
167
+ kind: page
168
+ value: ''
169
+ - id: azure-baa
170
+ url: https://learn.microsoft.com/en-us/azure/compliance/offerings/offering-hipaa-us
171
+ fetch: conditional_http
172
+ normaliser: html-default
173
+ cited_regions:
174
+ - id: page
175
+ locator:
176
+ kind: page
177
+ value: ''
178
+ - id: azure-soc2
179
+ url: https://learn.microsoft.com/en-us/compliance/regulatory/offering-soc-2
180
+ fetch: conditional_http
181
+ normaliser: html-default
182
+ cited_regions:
183
+ - id: page
184
+ locator:
185
+ kind: page
186
+ value: ''
187
+ - id: openai-data
188
+ url: https://platform.openai.com/docs/models/default-usage-policies-by-endpoint
189
+ fetch: conditional_http
190
+ normaliser: html-default
191
+ cited_regions:
192
+ - id: page
193
+ locator:
194
+ kind: page
195
+ value: ''
196
+ - id: gemini-pricing
197
+ url: https://ai.google.dev/gemini-api/docs/pricing
198
+ fetch: conditional_http
199
+ normaliser: html-default
200
+ cited_regions:
201
+ - id: page
202
+ locator:
203
+ kind: page
204
+ value: ''
205
+ - id: gemini-3-1-pro-preview
206
+ locator:
207
+ kind: heading
208
+ value: gemini-3.1-pro-preview
209
+ - id: gemini-3-5-flash
210
+ locator:
211
+ kind: heading
212
+ value: gemini-3.5-flash
213
+ - id: gemini-3-7-flash
214
+ locator:
215
+ kind: heading
216
+ value: gemini-3.7-flash
217
+ - id: gemini-3-8-flash
218
+ locator:
219
+ kind: heading
220
+ value: gemini-3.8-flash
221
+ - id: gemini-retention
222
+ url: https://ai.google.dev/gemini-api/docs/usage-policies
223
+ fetch: conditional_http
224
+ normaliser: html-default
225
+ cited_regions:
226
+ - id: page
227
+ locator:
228
+ kind: page
229
+ value: ''
230
+ - id: gemini-zdr
231
+ url: https://ai.google.dev/gemini-api/docs/zdr
232
+ fetch: conditional_http
233
+ normaliser: html-default
234
+ cited_regions:
235
+ - id: page
236
+ locator:
237
+ kind: page
238
+ value: ''
239
+ - id: openai-gpt-5-4-pricing
240
+ url: https://developers.openai.com/api/docs/models/gpt-5.4
241
+ fetch: conditional_http
242
+ normaliser: html-default
243
+ cited_regions:
244
+ - id: page
245
+ locator:
246
+ kind: page
247
+ value: ''
248
+ - id: openai-gpt-5-6-sol-pricing
249
+ url: https://developers.openai.com/api/docs/models/gpt-5.6-sol
250
+ fetch: conditional_http
251
+ normaliser: html-default
252
+ cited_regions:
253
+ - id: page
254
+ locator:
255
+ kind: page
256
+ value: ''
257
+ - id: openai-gpt-6-astra-pricing
258
+ url: https://developers.openai.com/api/docs/models/gpt-6-astra
259
+ fetch: conditional_http
260
+ normaliser: html-default
261
+ cited_regions:
262
+ - id: page
263
+ locator:
264
+ kind: page
265
+ value: ''
266
+ - id: openai-gpt-6-sol-pricing
267
+ url: https://developers.openai.com/api/docs/models/gpt-6-sol
268
+ fetch: conditional_http
269
+ normaliser: html-default
270
+ cited_regions:
271
+ - id: page
272
+ locator:
273
+ kind: page
274
+ value: ''
275
+ - id: model-143-alibaba-modelstudio-terms
276
+ url: https://www.alibabacloud.com/help/en/legal/latest/alibaba-cloud-international-website-product-terms-of-service-v-3-8-0
277
+ fetch: http
278
+ normaliser: html-default
279
+ cited_regions:
280
+ - id: audit
281
+ locator:
282
+ kind: page
283
+ value: ''
284
+ - id: model-143-anthropic-claude-fable-5
285
+ url: https://platform.claude.com/docs/en/models/fable-5/overview
286
+ fetch: http
287
+ normaliser: html-default
288
+ cited_regions:
289
+ - id: model-spec
290
+ locator:
291
+ kind: page
292
+ value: ''
293
+ - id: model-143-anthropic-claude-fable-5-1
294
+ url: https://platform.claude.com/docs/en/models/fable-5-1/overview
295
+ fetch: http
296
+ normaliser: html-default
297
+ cited_regions:
298
+ - id: model-spec
299
+ locator:
300
+ kind: page
301
+ value: ''
302
+ - id: model-143-anthropic-claude-opus-4-6
303
+ url: https://platform.claude.com/docs/en/models/opus-4-6/overview
304
+ fetch: http
305
+ normaliser: html-default
306
+ cited_regions:
307
+ - id: model-spec
308
+ locator:
309
+ kind: page
310
+ value: ''
311
+ - id: model-143-anthropic-claude-opus-4-7
312
+ url: https://platform.claude.com/docs/en/models/opus-4-7/overview
313
+ fetch: http
314
+ normaliser: html-default
315
+ cited_regions:
316
+ - id: model-spec
317
+ locator:
318
+ kind: page
319
+ value: ''
320
+ - id: model-143-anthropic-claude-opus-5
321
+ url: https://platform.claude.com/docs/en/models/opus-5/overview
322
+ fetch: http
323
+ normaliser: html-default
324
+ cited_regions:
325
+ - id: model-spec
326
+ locator:
327
+ kind: page
328
+ value: ''
329
+ - id: model-143-anthropic-claude-opus-5-5
330
+ url: https://platform.claude.com/docs/en/models/opus-5-5/overview
331
+ fetch: http
332
+ normaliser: html-default
333
+ cited_regions:
334
+ - id: model-spec
335
+ locator:
336
+ kind: page
337
+ value: ''
338
+ - id: model-143-anthropic-commercial-terms
339
+ url: https://www.anthropic.com/legal/commercial-terms
340
+ fetch: http
341
+ normaliser: html-default
342
+ cited_regions:
343
+ - id: audit
344
+ locator:
345
+ kind: page
346
+ value: ''
347
+ - id: model-143-anthropic-models-overview
348
+ url: https://platform.claude.com/docs/en/models/overview
349
+ fetch: http
350
+ normaliser: html-default
351
+ cited_regions:
352
+ - id: audit
353
+ locator:
354
+ kind: page
355
+ value: ''
356
+ - id: model-143-anthropic-streaming
357
+ url: https://platform.claude.com/docs/en/build-with-claude/streaming
358
+ fetch: http
359
+ normaliser: html-default
360
+ cited_regions:
361
+ - id: audit
362
+ locator:
363
+ kind: page
364
+ value: ''
365
+ - id: model-143-anthropic-structured-outputs
366
+ url: https://platform.claude.com/docs/en/build-with-claude/structured-outputs
367
+ fetch: http
368
+ normaliser: html-default
369
+ cited_regions:
370
+ - id: audit
371
+ locator:
372
+ kind: page
373
+ value: ''
374
+ - id: model-143-apache-2-license
375
+ url: https://www.apache.org/licenses/LICENSE-2.0.txt
376
+ fetch: http
377
+ normaliser: text-default
378
+ cited_regions:
379
+ - id: audit
380
+ locator:
381
+ kind: page
382
+ value: ''
383
+ - id: model-143-deepseek-deepseek-v4-pro
384
+ url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/resolve/main/README.md
385
+ fetch: http
386
+ normaliser: text-default
387
+ cited_regions:
388
+ - id: model-spec
389
+ locator:
390
+ kind: page
391
+ value: ''
392
+ - id: model-143-deepseek-function-calling
393
+ url: https://api-docs.deepseek.com/guides/function_calling
394
+ fetch: http
395
+ normaliser: html-default
396
+ cited_regions:
397
+ - id: audit
398
+ locator:
399
+ kind: page
400
+ value: ''
401
+ - id: model-143-deepseek-json-output
402
+ url: https://api-docs.deepseek.com/guides/json_mode
403
+ fetch: http
404
+ normaliser: html-default
405
+ cited_regions:
406
+ - id: audit
407
+ locator:
408
+ kind: page
409
+ value: ''
410
+ - id: model-143-deepseek-streaming
411
+ url: https://api-docs.deepseek.com/guides/streaming
412
+ fetch: http
413
+ normaliser: html-default
414
+ cited_regions:
415
+ - id: audit
416
+ locator:
417
+ kind: page
418
+ value: ''
419
+ - id: model-143-deepseek-v4-license
420
+ url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/raw/main/LICENSE
421
+ fetch: http
422
+ normaliser: text-default
423
+ cited_regions:
424
+ - id: audit
425
+ locator:
426
+ kind: page
427
+ value: ''
428
+ - id: model-143-evidence-arena-text-json
429
+ volatility: live
430
+ url: https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset
431
+ fetch: http
432
+ normaliser: text-default
433
+ cited_regions:
434
+ - id: rows
435
+ locator:
436
+ kind: page
437
+ value: ''
438
+ - id: model-143-evidence-arena-vision-json
439
+ volatility: live
440
+ url: https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset
441
+ fetch: http
442
+ normaliser: text-default
443
+ cited_regions:
444
+ - id: rows
445
+ locator:
446
+ kind: page
447
+ value: ''
448
+ - id: model-143-evidence-arena-webdev-json
449
+ volatility: live
450
+ url: https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset
451
+ fetch: http
452
+ normaliser: text-default
453
+ cited_regions:
454
+ - id: rows
455
+ locator:
456
+ kind: page
457
+ value: ''
458
+ - id: model-143-evidence-epoch-frontiermath-tiers-1-3-v2-csv
459
+ volatility: live
460
+ url: https://epoch.ai/frontiermath
461
+ fetch: http
462
+ normaliser: text-default
463
+ cited_regions:
464
+ - id: rows
465
+ locator:
466
+ kind: page
467
+ value: ''
468
+ - id: model-143-evidence-epoch-gpqa-diamond-csv
469
+ volatility: live
470
+ url: https://epoch.ai/benchmarks/gpqa-diamond
471
+ fetch: http
472
+ normaliser: text-default
473
+ cited_regions:
474
+ - id: rows
475
+ locator:
476
+ kind: page
477
+ value: ''
478
+ - id: model-143-evidence-epoch-swe-bench-verified-csv
479
+ volatility: live
480
+ url: https://epoch.ai/benchmarks/swe-bench-verified
481
+ fetch: http
482
+ normaliser: text-default
483
+ cited_regions:
484
+ - id: rows
485
+ locator:
486
+ kind: page
487
+ value: ''
488
+ - id: model-143-evidence-mteb-eng-v2-json
489
+ volatility: live
490
+ url: https://mteb-leaderboard-backend.hf.space/v1/benchmarks/MTEB(eng,%20v2)/scores
491
+ fetch: http
492
+ normaliser: text-default
493
+ cited_regions:
494
+ - id: rows
495
+ locator:
496
+ kind: page
497
+ value: ''
498
+ - id: model-143-evidence-mteb-multilingual-v2-json
499
+ volatility: live
500
+ url: https://mteb-leaderboard-backend.hf.space/v1/benchmarks/MTEB(Multilingual,%20v2)/scores
501
+ fetch: http
502
+ normaliser: text-default
503
+ cited_regions:
504
+ - id: rows
505
+ locator:
506
+ kind: page
507
+ value: ''
508
+ - id: model-143-evidence-scale-hle-json
509
+ volatility: live
510
+ url: https://labs.scale.com/leaderboard/humanitys_last_exam
511
+ fetch: http
512
+ normaliser: text-default
513
+ cited_regions:
514
+ - id: rows
515
+ locator:
516
+ kind: page
517
+ value: ''
518
+ - id: model-143-evidence-terminal-bench-4-0-json
519
+ volatility: live
520
+ url: https://www.tbench.ai/
521
+ fetch: http
522
+ normaliser: text-default
523
+ cited_regions:
524
+ - id: rows
525
+ locator:
526
+ kind: page
527
+ value: ''
528
+ - id: model-143-glm-5-3-license
529
+ url: https://huggingface.co/zai-org/GLM-5.3/raw/main/LICENSE
530
+ fetch: http
531
+ normaliser: text-default
532
+ cited_regions:
533
+ - id: audit
534
+ locator:
535
+ kind: page
536
+ value: ''
537
+ - id: model-143-google-company
538
+ url: https://about.google/company-info/
539
+ fetch: http
540
+ normaliser: html-default
541
+ cited_regions:
542
+ - id: audit
543
+ locator:
544
+ kind: page
545
+ value: ''
546
+ - id: model-143-google-deprecations
547
+ url: https://ai.google.dev/gemini-api/docs/deprecations
548
+ fetch: http
549
+ normaliser: html-default
550
+ cited_regions:
551
+ - id: audit
552
+ locator:
553
+ kind: page
554
+ value: ''
555
+ - id: model-143-google-gemini-3-1-pro-preview
556
+ url: https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview
557
+ fetch: http
558
+ normaliser: html-default
559
+ cited_regions:
560
+ - id: model-spec
561
+ locator:
562
+ kind: page
563
+ value: ''
564
+ - id: model-143-google-gemini-3-5-flash
565
+ url: https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash
566
+ fetch: http
567
+ normaliser: html-default
568
+ cited_regions:
569
+ - id: model-spec
570
+ locator:
571
+ kind: page
572
+ value: ''
573
+ - id: model-143-google-gemini-3-7-flash
574
+ url: https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash
575
+ fetch: http
576
+ normaliser: html-default
577
+ cited_regions:
578
+ - id: model-spec
579
+ locator:
580
+ kind: page
581
+ value: ''
582
+ - id: model-143-google-gemini-3-8-flash
583
+ url: https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash
584
+ fetch: http
585
+ normaliser: html-default
586
+ cited_regions:
587
+ - id: model-spec
588
+ locator:
589
+ kind: page
590
+ value: ''
591
+ - id: model-143-google-sec
592
+ url: https://data.sec.gov/submissions/CIK0001652044.json
593
+ fetch: http
594
+ normaliser: text-default
595
+ cited_regions:
596
+ - id: audit
597
+ locator:
598
+ kind: page
599
+ value: ''
600
+ - id: model-143-google-streaming
601
+ url: https://ai.google.dev/gemini-api/docs/text-generation
602
+ fetch: http
603
+ normaliser: html-default
604
+ cited_regions:
605
+ - id: audit
606
+ locator:
607
+ kind: page
608
+ value: ''
609
+ - id: model-143-google-terms
610
+ url: https://ai.google.dev/gemini-api/terms
611
+ fetch: http
612
+ normaliser: html-default
613
+ cited_regions:
614
+ - id: audit
615
+ locator:
616
+ kind: page
617
+ value: ''
618
+ - id: model-143-hf-metadata-deepseek-deepseek-v4-pro
619
+ url: https://huggingface.co/api/models/deepseek-ai/DeepSeek-V4-Pro
620
+ fetch: http
621
+ normaliser: text-default
622
+ cited_regions:
623
+ - id: audit
624
+ locator:
625
+ kind: page
626
+ value: ''
627
+ - id: model-143-hf-metadata-jcorners-ingot-8b-r3
628
+ url: https://huggingface.co/api/models/JCorners/Ingot-8B-R3
629
+ fetch: http
630
+ normaliser: text-default
631
+ cited_regions:
632
+ - id: audit
633
+ locator:
634
+ kind: page
635
+ value: ''
636
+ - id: model-143-hf-metadata-kingsoft-qzhou-embedding
637
+ url: https://huggingface.co/api/models/Kingsoft-LLM/QZhou-Embedding
638
+ fetch: http
639
+ normaliser: text-default
640
+ cited_regions:
641
+ - id: audit
642
+ locator:
643
+ kind: page
644
+ value: ''
645
+ - id: model-143-hf-metadata-microsoft-harrier-oss-v1-27b
646
+ url: https://huggingface.co/api/models/microsoft/harrier-oss-v1-27b
647
+ fetch: http
648
+ normaliser: text-default
649
+ cited_regions:
650
+ - id: audit
651
+ locator:
652
+ kind: page
653
+ value: ''
654
+ - id: model-143-hf-metadata-moonshot-kimi-k2-6
655
+ url: https://huggingface.co/api/models/moonshotai/Kimi-K2.6
656
+ fetch: http
657
+ normaliser: text-default
658
+ cited_regions:
659
+ - id: audit
660
+ locator:
661
+ kind: page
662
+ value: ''
663
+ - id: model-143-hf-metadata-moonshot-kimi-k3
664
+ url: https://huggingface.co/api/models/moonshotai/Kimi-K3
665
+ fetch: http
666
+ normaliser: text-default
667
+ cited_regions:
668
+ - id: audit
669
+ locator:
670
+ kind: page
671
+ value: ''
672
+ - id: model-143-hf-metadata-querit-querit
673
+ url: https://huggingface.co/api/models/Querit/Querit
674
+ fetch: http
675
+ normaliser: text-default
676
+ cited_regions:
677
+ - id: audit
678
+ locator:
679
+ kind: page
680
+ value: ''
681
+ - id: model-143-hf-metadata-querit-querit-4b
682
+ url: https://huggingface.co/api/models/Querit/Querit-4B
683
+ fetch: http
684
+ normaliser: text-default
685
+ cited_regions:
686
+ - id: audit
687
+ locator:
688
+ kind: page
689
+ value: ''
690
+ - id: model-143-hf-metadata-qwen-qwen3-8-flash-next
691
+ url: https://huggingface.co/api/models/Qwen/Qwen3.8-Flash-Next
692
+ fetch: http
693
+ normaliser: text-default
694
+ cited_regions:
695
+ - id: audit
696
+ locator:
697
+ kind: page
698
+ value: ''
699
+ - id: model-143-hf-metadata-tencent-kalm-embedding-gemma3-12b-2511
700
+ url: https://huggingface.co/api/models/tencent/KaLM-Embedding-Gemma3-12B-2511
701
+ fetch: http
702
+ normaliser: text-default
703
+ cited_regions:
704
+ - id: audit
705
+ locator:
706
+ kind: page
707
+ value: ''
708
+ - id: model-143-hf-metadata-zhipu-glm-5-2
709
+ url: https://huggingface.co/api/models/zai-org/GLM-5.2
710
+ fetch: http
711
+ normaliser: text-default
712
+ cited_regions:
713
+ - id: audit
714
+ locator:
715
+ kind: page
716
+ value: ''
717
+ - id: model-143-hf-metadata-zhipu-glm-5-3
718
+ url: https://huggingface.co/api/models/zai-org/GLM-5.3
719
+ fetch: http
720
+ normaliser: text-default
721
+ cited_regions:
722
+ - id: audit
723
+ locator:
724
+ kind: page
725
+ value: ''
726
+ - id: model-143-jcorners-ingot-8b-r3
727
+ url: https://huggingface.co/JCorners/Ingot-8B-R3/resolve/main/README.md
728
+ fetch: http
729
+ normaliser: text-default
730
+ cited_regions:
731
+ - id: model-spec
732
+ locator:
733
+ kind: page
734
+ value: ''
735
+ - id: model-143-kalm-license
736
+ url: https://huggingface.co/tencent/KaLM-Embedding-Gemma3-12B-2511/raw/main/LICENSE.txt
737
+ fetch: http
738
+ normaliser: text-default
739
+ cited_regions:
740
+ - id: audit
741
+ locator:
742
+ kind: page
743
+ value: ''
744
+ - id: model-143-kimi-k2-6-guide
745
+ url: https://platform.moonshot.ai/docs/guide/use-kimi-k2-thinking-model
746
+ fetch: http
747
+ normaliser: html-default
748
+ cited_regions:
749
+ - id: audit
750
+ locator:
751
+ kind: page
752
+ value: ''
753
+ - id: model-143-kimi-k2-6-license
754
+ url: https://huggingface.co/moonshotai/Kimi-K2.6/raw/main/LICENSE
755
+ fetch: http
756
+ normaliser: text-default
757
+ cited_regions:
758
+ - id: audit
759
+ locator:
760
+ kind: page
761
+ value: ''
762
+ - id: model-143-kimi-k3-guide
763
+ url: https://platform.kimi.ai/docs/guide/kimi-k3-quickstart
764
+ fetch: http
765
+ normaliser: html-default
766
+ cited_regions:
767
+ - id: audit
768
+ locator:
769
+ kind: page
770
+ value: ''
771
+ - id: model-143-kimi-k3-license
772
+ url: https://huggingface.co/moonshotai/Kimi-K3/raw/main/LICENSE
773
+ fetch: http
774
+ normaliser: text-default
775
+ cited_regions:
776
+ - id: audit
777
+ locator:
778
+ kind: page
779
+ value: ''
780
+ - id: model-143-kingsoft-qzhou-embedding
781
+ url: https://huggingface.co/Kingsoft-LLM/QZhou-Embedding/raw/main/README.md
782
+ fetch: http
783
+ normaliser: text-default
784
+ cited_regions:
785
+ - id: model-spec
786
+ locator:
787
+ kind: page
788
+ value: ''
789
+ - id: model-143-meta-company
790
+ url: https://about.fb.com/company-info/
791
+ fetch: http
792
+ normaliser: html-default
793
+ cited_regions:
794
+ - id: audit
795
+ locator:
796
+ kind: page
797
+ value: ''
798
+ - id: model-143-meta-model-api
799
+ url: https://ai.meta.com/llama/
800
+ fetch: http
801
+ normaliser: html-default
802
+ cited_regions:
803
+ - id: audit
804
+ locator:
805
+ kind: page
806
+ value: ''
807
+ - id: model-143-meta-muse-spark
808
+ url: https://ai.developer.meta.com/docs/models.md
809
+ fetch: http
810
+ normaliser: text-default
811
+ cited_regions:
812
+ - id: model-spec
813
+ locator:
814
+ kind: page
815
+ value: ''
816
+ - id: model-143-meta-muse-spark-1-1
817
+ url: https://ai.developer.meta.com/docs/models.md
818
+ fetch: http
819
+ normaliser: text-default
820
+ cited_regions:
821
+ - id: model-spec
822
+ locator:
823
+ kind: page
824
+ value: ''
825
+ - id: model-143-meta-muse-spark-1-3
826
+ url: https://ai.developer.meta.com/docs/models.md
827
+ fetch: http
828
+ normaliser: text-default
829
+ cited_regions:
830
+ - id: model-spec
831
+ locator:
832
+ kind: page
833
+ value: ''
834
+ - id: model-143-meta-release-index
835
+ url: https://ai.meta.com/events/
836
+ fetch: rendered
837
+ normaliser: text-default
838
+ cited_regions:
839
+ - id: audit
840
+ locator:
841
+ kind: page
842
+ value: ''
843
+ - id: model-143-meta-sec
844
+ url: https://data.sec.gov/submissions/CIK0001326801.json
845
+ fetch: http
846
+ normaliser: text-default
847
+ cited_regions:
848
+ - id: audit
849
+ locator:
850
+ kind: page
851
+ value: ''
852
+ - id: model-143-microsoft-harrier-oss-v1-27b
853
+ url: https://huggingface.co/microsoft/harrier-oss-v1-27b/raw/main/README.md
854
+ fetch: http
855
+ normaliser: text-default
856
+ cited_regions:
857
+ - id: model-spec
858
+ locator:
859
+ kind: page
860
+ value: ''
861
+ - id: model-143-mit-license
862
+ url: https://opensource.org/license/mit
863
+ fetch: http
864
+ normaliser: html-default
865
+ cited_regions:
866
+ - id: audit
867
+ locator:
868
+ kind: page
869
+ value: ''
870
+ - id: model-143-moonshot-kimi-k2-6
871
+ url: https://huggingface.co/moonshotai/Kimi-K2.6/resolve/main/README.md
872
+ fetch: http
873
+ normaliser: text-default
874
+ cited_regions:
875
+ - id: model-spec
876
+ locator:
877
+ kind: page
878
+ value: ''
879
+ - id: model-143-moonshot-kimi-k3
880
+ url: https://huggingface.co/moonshotai/Kimi-K3/resolve/main/README.md
881
+ fetch: http
882
+ normaliser: text-default
883
+ cited_regions:
884
+ - id: model-spec
885
+ locator:
886
+ kind: page
887
+ value: ''
888
+ - id: model-143-openai-changelog
889
+ url: https://developers.openai.com/api/docs/changelog
890
+ fetch: http
891
+ normaliser: html-default
892
+ cited_regions:
893
+ - id: audit
894
+ locator:
895
+ kind: page
896
+ value: ''
897
+ - id: model-143-openai-gpt-5-4
898
+ url: https://developers.openai.com/api/docs/models/gpt-5.4
899
+ fetch: http
900
+ normaliser: html-default
901
+ cited_regions:
902
+ - id: model-spec
903
+ locator:
904
+ kind: page
905
+ value: ''
906
+ - id: model-143-openai-gpt-5-6-sol
907
+ url: https://developers.openai.com/api/docs/models/gpt-5.6-sol
908
+ fetch: http
909
+ normaliser: html-default
910
+ cited_regions:
911
+ - id: model-spec
912
+ locator:
913
+ kind: page
914
+ value: ''
915
+ - id: model-143-openai-gpt-6-astra
916
+ url: https://developers.openai.com/api/docs/models/gpt-6-astra
917
+ fetch: http
918
+ normaliser: html-default
919
+ cited_regions:
920
+ - id: model-spec
921
+ locator:
922
+ kind: page
923
+ value: ''
924
+ - id: model-143-openai-gpt-6-sol
925
+ url: https://developers.openai.com/api/docs/models/gpt-6-sol
926
+ fetch: http
927
+ normaliser: html-default
928
+ cited_regions:
929
+ - id: model-spec
930
+ locator:
931
+ kind: page
932
+ value: ''
933
+ - id: model-143-openai-models-overview
934
+ url: https://developers.openai.com/api/docs/models/all
935
+ fetch: http
936
+ normaliser: html-default
937
+ cited_regions:
938
+ - id: audit
939
+ locator:
940
+ kind: page
941
+ value: ''
942
+ - id: model-143-openai-reasoning
943
+ url: https://developers.openai.com/api/docs/guides/reasoning
944
+ fetch: http
945
+ normaliser: html-default
946
+ cited_regions:
947
+ - id: audit
948
+ locator:
949
+ kind: page
950
+ value: ''
951
+ - id: model-143-openai-services-agreement
952
+ url: https://openai.com/policies/services-agreement/
953
+ fetch: rendered
954
+ normaliser: text-default
955
+ cited_regions:
956
+ - id: audit
957
+ locator:
958
+ kind: page
959
+ value: ''
960
+ - id: model-143-querit-querit
961
+ url: https://huggingface.co/Querit/Querit/resolve/main/README.md
962
+ fetch: http
963
+ normaliser: text-default
964
+ cited_regions:
965
+ - id: model-spec
966
+ locator:
967
+ kind: page
968
+ value: ''
969
+ - id: model-143-querit-querit-4b
970
+ url: https://huggingface.co/Querit/Querit-4B/resolve/main/README.md
971
+ fetch: http
972
+ normaliser: text-default
973
+ cited_regions:
974
+ - id: model-spec
975
+ locator:
976
+ kind: page
977
+ value: ''
978
+ - id: model-143-qwen-qwen3-8-flash-next
979
+ url: https://huggingface.co/Qwen/Qwen3.8-Flash-Next/resolve/main/README.md
980
+ fetch: http
981
+ normaliser: text-default
982
+ cited_regions:
983
+ - id: model-spec
984
+ locator:
985
+ kind: page
986
+ value: ''
987
+ - id: model-143-qwen-qwen3-8-max-0902
988
+ url: https://docs.modelstudio.console.alibabacloud.com/en/model-studio/qwen3-8-max
989
+ fetch: http
990
+ normaliser: html-default
991
+ cited_regions:
992
+ - id: model-spec
993
+ locator:
994
+ kind: page
995
+ value: ''
996
+ - id: model-143-qwen3-8-flash-next-license
997
+ url: https://huggingface.co/Qwen/Qwen3.8-Flash-Next/raw/main/LICENSE
998
+ fetch: http
999
+ normaliser: text-default
1000
+ cited_regions:
1001
+ - id: audit
1002
+ locator:
1003
+ kind: page
1004
+ value: ''
1005
+ - id: model-143-tencent-kalm-embedding-gemma3-12b-2511
1006
+ url: https://huggingface.co/tencent/KaLM-Embedding-Gemma3-12B-2511/raw/main/README.md
1007
+ fetch: http
1008
+ normaliser: text-default
1009
+ cited_regions:
1010
+ - id: model-spec
1011
+ locator:
1012
+ kind: page
1013
+ value: ''
1014
+ - id: model-143-typesafe-jev-1-13
1015
+ url: https://docs.typesafe.ai/
1016
+ fetch: http
1017
+ normaliser: html-default
1018
+ cited_regions:
1019
+ - id: model-spec
1020
+ locator:
1021
+ kind: page
1022
+ value: ''
1023
+ - id: model-143-typesafe-models
1024
+ url: https://docs.typesafe.ai/models.md
1025
+ fetch: http
1026
+ normaliser: text-default
1027
+ cited_regions:
1028
+ - id: audit
1029
+ locator:
1030
+ kind: page
1031
+ value: ''
1032
+ - id: model-143-typesafe-system-one
1033
+ url: https://docs.typesafe.ai/concepts/system-one.md
1034
+ fetch: http
1035
+ normaliser: text-default
1036
+ cited_regions:
1037
+ - id: audit
1038
+ locator:
1039
+ kind: page
1040
+ value: ''
1041
+ - id: model-143-typesafe-terms
1042
+ url: https://typesafe.ai/legal/terms
1043
+ fetch: http
1044
+ normaliser: html-default
1045
+ cited_regions:
1046
+ - id: audit
1047
+ locator:
1048
+ kind: page
1049
+ value: ''
1050
+ - id: model-143-xai-enterprise-faq
1051
+ url: https://x.ai/legal/faq-enterprise
1052
+ fetch: http
1053
+ normaliser: html-default
1054
+ cited_regions:
1055
+ - id: audit
1056
+ locator:
1057
+ kind: page
1058
+ value: ''
1059
+ - id: model-143-xai-enterprise-terms
1060
+ url: https://x.ai/legal/terms-of-service-enterprise
1061
+ fetch: http
1062
+ normaliser: html-default
1063
+ cited_regions:
1064
+ - id: audit
1065
+ locator:
1066
+ kind: page
1067
+ value: ''
1068
+ - id: model-143-xai-function-calling
1069
+ url: https://docs.x.ai/developers/tools/function-calling
1070
+ fetch: http
1071
+ normaliser: html-default
1072
+ cited_regions:
1073
+ - id: audit
1074
+ locator:
1075
+ kind: page
1076
+ value: ''
1077
+ - id: model-143-xai-grok-4-7
1078
+ url: https://docs.x.ai/docs/models/grok-4-7
1079
+ fetch: http
1080
+ normaliser: html-default
1081
+ cited_regions:
1082
+ - id: model-spec
1083
+ locator:
1084
+ kind: page
1085
+ value: ''
1086
+ - id: model-143-xai-structured-outputs
1087
+ url: https://docs.x.ai/developers/model-capabilities/text/structured-outputs
1088
+ fetch: http
1089
+ normaliser: html-default
1090
+ cited_regions:
1091
+ - id: audit
1092
+ locator:
1093
+ kind: page
1094
+ value: ''
1095
+ - id: model-143-zai-glm-5-2-guide
1096
+ url: https://docs.z.ai/guides/llm/glm-5.2
1097
+ fetch: http
1098
+ normaliser: html-default
1099
+ cited_regions:
1100
+ - id: audit
1101
+ locator:
1102
+ kind: page
1103
+ value: ''
1104
+ - id: model-143-zai-glm-5-3-guide
1105
+ url: https://docs.z.ai/guides/llm/glm-5.3
1106
+ fetch: http
1107
+ normaliser: html-default
1108
+ cited_regions:
1109
+ - id: audit
1110
+ locator:
1111
+ kind: page
1112
+ value: ''
1113
+ - id: model-143-zhipu-glm-5-2
1114
+ url: https://huggingface.co/zai-org/GLM-5.2/resolve/main/README.md
1115
+ fetch: http
1116
+ normaliser: text-default
1117
+ cited_regions:
1118
+ - id: model-spec
1119
+ locator:
1120
+ kind: page
1121
+ value: ''
1122
+ - id: model-143-zhipu-glm-5-3
1123
+ url: https://huggingface.co/zai-org/GLM-5.3/resolve/main/README.md
1124
+ fetch: http
1125
+ normaliser: text-default
1126
+ cited_regions:
1127
+ - id: model-spec
1128
+ locator:
1129
+ kind: page
1130
+ value: ''
1131
+ - id: deepseek-v4-pricing
1132
+ url: https://api-docs.deepseek.com/quick_start/pricing/
1133
+ fetch: conditional_http
1134
+ normaliser: html-default
1135
+ cited_regions:
1136
+ - id: pricing-table
1137
+ locator:
1138
+ kind: table
1139
+ value: '0'
1140
+ - id: xai-grok-4-7
1141
+ url: https://docs.x.ai/developers/models/grok-4.7
1142
+ fetch: conditional_http
1143
+ normaliser: html-default
1144
+ cited_regions:
1145
+ - id: page
1146
+ locator:
1147
+ kind: page
1148
+ value: ''
1149
+ - id: xai-security
1150
+ url: https://docs.x.ai/developers/faq/security
1151
+ fetch: conditional_http
1152
+ normaliser: html-default
1153
+ cited_regions:
1154
+ - id: page
1155
+ locator:
1156
+ kind: page
1157
+ value: ''
1158
+ - id: zai-pricing
1159
+ url: https://docs.z.ai/guides/overview/pricing.md
1160
+ fetch: conditional_http
1161
+ normaliser: text-default
1162
+ cited_regions:
1163
+ - id: page
1164
+ locator:
1165
+ kind: page
1166
+ value: ''
1167
+ - id: zai-privacy
1168
+ url: https://docs.z.ai/legal-agreement/privacy-policy.md
1169
+ fetch: conditional_http
1170
+ normaliser: text-default
1171
+ cited_regions:
1172
+ - id: page
1173
+ locator:
1174
+ kind: page
1175
+ value: ''
1176
+ - id: alibaba-model-studio-pricing
1177
+ url: https://www.alibabacloud.com/help/en/model-studio/model-pricing
1178
+ fetch: conditional_http
1179
+ normaliser: html-default
1180
+ cited_regions:
1181
+ - id: singapore-qwen-max
1182
+ locator:
1183
+ kind: table
1184
+ value: '0'
1185
+ - id: alibaba-model-studio-privacy
1186
+ url: https://www.alibabacloud.com/help/en/model-studio/privacy-notice
1187
+ fetch: conditional_http
1188
+ normaliser: html-default
1189
+ cited_regions:
1190
+ - id: page
1191
+ locator:
1192
+ kind: page
1193
+ value: ''
1194
+ - id: meta-model-api-pricing
1195
+ url: https://ai.developer.meta.com/docs/pricing-rate-limits.md
1196
+ fetch: conditional_http
1197
+ normaliser: text-default
1198
+ cited_regions:
1199
+ - id: page
1200
+ locator:
1201
+ kind: page
1202
+ value: ''
1203
+ - id: typesafe-models
1204
+ url: https://docs.typesafe.ai/models.md
1205
+ fetch: conditional_http
1206
+ normaliser: text-default
1207
+ cited_regions:
1208
+ - id: page
1209
+ locator:
1210
+ kind: page
1211
+ value: ''
1212
+ # MODEL-158: the Fable 5.1 system card is a PDF, which the normaliser cannot read
1213
+ # yet; its retained copy is the pypdf text of section 8.6 (Terminal-Bench 4.0).
1214
+ - id: model-158-anthropic-claude-fable-5-1-system-card
1215
+ url: https://www.anthropic.com/claude-fable-5-1-system-card
1216
+ fetch: http
1217
+ normaliser: text-default
1218
+ cited_regions:
1219
+ - id: terminal-bench-4-0
1220
+ locator:
1221
+ kind: page
1222
+ value: ''
1223
+ # MODEL-160: board projections (JSON rows) of machine-readable boards; read 2026-09-25.
1224
+ - id: model-160-arena-text
1225
+ volatility: live
1226
+ url: https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/1880dbebff5ba3e2dd3865ecf6fc43539c2099db/text/latest-00000-of-00001.parquet
1227
+ fetch: http
1228
+ normaliser: text-default
1229
+ cited_regions:
1230
+ - id: rows
1231
+ locator:
1232
+ kind: page
1233
+ value: ''
1234
+ - id: model-160-arena-text-style-control
1235
+ volatility: live
1236
+ url: https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/1880dbebff5ba3e2dd3865ecf6fc43539c2099db/text_style_control/latest-00000-of-00001.parquet
1237
+ fetch: http
1238
+ normaliser: text-default
1239
+ cited_regions:
1240
+ - id: rows
1241
+ locator:
1242
+ kind: page
1243
+ value: ''
1244
+ - id: model-160-arena-vision
1245
+ volatility: live
1246
+ url: https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/1880dbebff5ba3e2dd3865ecf6fc43539c2099db/vision/latest-00000-of-00001.parquet
1247
+ fetch: http
1248
+ normaliser: text-default
1249
+ cited_regions:
1250
+ - id: rows
1251
+ locator:
1252
+ kind: page
1253
+ value: ''
1254
+ - id: model-160-arena-vision-style-control
1255
+ volatility: live
1256
+ url: https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/1880dbebff5ba3e2dd3865ecf6fc43539c2099db/vision_style_control/latest-00000-of-00001.parquet
1257
+ fetch: http
1258
+ normaliser: text-default
1259
+ cited_regions:
1260
+ - id: rows
1261
+ locator:
1262
+ kind: page
1263
+ value: ''
1264
+ - id: model-160-cursorbench
1265
+ volatility: live
1266
+ url: https://cursor.com/cursorbench
1267
+ fetch: http
1268
+ normaliser: text-default
1269
+ cited_regions:
1270
+ - id: rows
1271
+ locator:
1272
+ kind: page
1273
+ value: ''
1274
+ - id: model-160-deepswe-v1-1
1275
+ volatility: live
1276
+ url: https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json
1277
+ fetch: http
1278
+ normaliser: text-default
1279
+ cited_regions:
1280
+ - id: rows
1281
+ locator:
1282
+ kind: page
1283
+ value: ''
1284
+ - id: model-160-epoch-simpleqa-verified-csv
1285
+ volatility: live
1286
+ url: https://epoch.ai/benchmarks/simpleqa-verified
1287
+ fetch: http
1288
+ normaliser: text-default
1289
+ cited_regions:
1290
+ - id: rows
1291
+ locator:
1292
+ kind: page
1293
+ value: ''
1294
+ - id: model-160-epoch-swe-bench-verified-csv
1295
+ volatility: live
1296
+ url: https://epoch.ai/benchmarks/swe-bench-verified
1297
+ fetch: http
1298
+ normaliser: text-default
1299
+ cited_regions:
1300
+ - id: rows
1301
+ locator:
1302
+ kind: page
1303
+ value: ''
1304
+ - id: model-160-frontiercode
1305
+ volatility: live
1306
+ url: https://cognition.com/frontiercode
1307
+ fetch: rendered
1308
+ normaliser: text-default
1309
+ cited_regions:
1310
+ - id: rows
1311
+ locator:
1312
+ kind: page
1313
+ value: ''
1314
+ - id: model-160-matharena-aime-2026
1315
+ volatility: live
1316
+ url: https://matharena.ai/competition_tables/aime--aime_2026
1317
+ fetch: http
1318
+ normaliser: text-default
1319
+ cited_regions:
1320
+ - id: rows
1321
+ locator:
1322
+ kind: page
1323
+ value: ''
1324
+ - id: model-160-metr-time-horizon-1-1
1325
+ volatility: live
1326
+ url: https://metr.org/assets/benchmark_results_1_1.yaml
1327
+ fetch: http
1328
+ normaliser: text-default
1329
+ cited_regions:
1330
+ - id: rows
1331
+ locator:
1332
+ kind: page
1333
+ value: ''
1334
+ - id: model-160-mteb-eng-v2
1335
+ volatility: live
1336
+ url: https://mteb-leaderboard-backend.hf.space/v1/benchmarks/MTEB(eng,%20v2)/scores
1337
+ fetch: http
1338
+ normaliser: text-default
1339
+ cited_regions:
1340
+ - id: rows
1341
+ locator:
1342
+ kind: page
1343
+ value: ''
1344
+ - id: model-160-osworld
1345
+ volatility: live
1346
+ url: https://osworld-v2.xlang.ai/
1347
+ fetch: rendered
1348
+ normaliser: text-default
1349
+ cited_regions:
1350
+ - id: rows
1351
+ locator:
1352
+ kind: page
1353
+ value: ''
1354
+ - id: model-160-scale-swe-bench-pro-public
1355
+ volatility: live
1356
+ url: https://labs.scale.com/leaderboard/swe_bench_pro_public
1357
+ fetch: http
1358
+ normaliser: text-default
1359
+ cited_regions:
1360
+ - id: rows
1361
+ locator:
1362
+ kind: page
1363
+ value: ''
1364
+ - id: model-160-swebench-leaderboard
1365
+ volatility: live
1366
+ url: https://www.swebench.com/
1367
+ fetch: http
1368
+ normaliser: text-default
1369
+ cited_regions:
1370
+ - id: rows
1371
+ locator:
1372
+ kind: page
1373
+ value: ''
1374
+ - id: model-160-tau-bench-claude-fable-5-sierra-2026-08-04
1375
+ volatility: live
1376
+ url: https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/claude-fable-5_sierra_2026-08-04/submission.json
1377
+ fetch: http
1378
+ normaliser: text-default
1379
+ cited_regions:
1380
+ - id: rows
1381
+ locator:
1382
+ kind: page
1383
+ value: ''
1384
+ - id: model-160-tau-bench-claude-opus-4-6-sierra-2026-05-05
1385
+ volatility: live
1386
+ url: https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/claude-opus-4-6_sierra_2026-05-05/submission.json
1387
+ fetch: http
1388
+ normaliser: text-default
1389
+ cited_regions:
1390
+ - id: rows
1391
+ locator:
1392
+ kind: page
1393
+ value: ''
1394
+ - id: model-160-tau-bench-claude-opus-4-7-sierra-2026-05-05
1395
+ volatility: live
1396
+ url: https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/claude-opus-4-7_sierra_2026-05-05/submission.json
1397
+ fetch: http
1398
+ normaliser: text-default
1399
+ cited_regions:
1400
+ - id: rows
1401
+ locator:
1402
+ kind: page
1403
+ value: ''
1404
+ - id: model-160-tau-bench-claude-opus-5-sierra-2026-08-04
1405
+ volatility: live
1406
+ url: https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/claude-opus-5_sierra_2026-08-04/submission.json
1407
+ fetch: http
1408
+ normaliser: text-default
1409
+ cited_regions:
1410
+ - id: rows
1411
+ locator:
1412
+ kind: page
1413
+ value: ''
1414
+ - id: model-160-tau-bench-gemini-3-1-pro-preview-sierra-2026-05-05
1415
+ volatility: live
1416
+ url: https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gemini-3-1-pro-preview_sierra_2026-05-05/submission.json
1417
+ fetch: http
1418
+ normaliser: text-default
1419
+ cited_regions:
1420
+ - id: rows
1421
+ locator:
1422
+ kind: page
1423
+ value: ''
1424
+ - id: model-160-tau-bench-glm-5-2-sierra-2026-08-04
1425
+ volatility: live
1426
+ url: https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/glm-5-2_sierra_2026-08-04/submission.json
1427
+ fetch: http
1428
+ normaliser: text-default
1429
+ cited_regions:
1430
+ - id: rows
1431
+ locator:
1432
+ kind: page
1433
+ value: ''
1434
+ - id: model-160-tau-bench-gpt-5-4-sierra-2026-03-25
1435
+ volatility: live
1436
+ url: https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-4_sierra_2026-03-25/submission.json
1437
+ fetch: http
1438
+ normaliser: text-default
1439
+ cited_regions:
1440
+ - id: rows
1441
+ locator:
1442
+ kind: page
1443
+ value: ''
1444
+ - id: model-160-tau-bench-gpt-5-6-sol-sierra-2026-08-04
1445
+ volatility: live
1446
+ url: https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-6-sol_sierra_2026-08-04/submission.json
1447
+ fetch: http
1448
+ normaliser: text-default
1449
+ cited_regions:
1450
+ - id: rows
1451
+ locator:
1452
+ kind: page
1453
+ value: ''
1454
+ - id: model-160-tau-bench-kimi-k3-sierra-2026-08-04
1455
+ volatility: live
1456
+ url: https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/kimi-k3_sierra_2026-08-04/submission.json
1457
+ fetch: http
1458
+ normaliser: text-default
1459
+ cited_regions:
1460
+ - id: rows
1461
+ locator:
1462
+ kind: page
1463
+ value: ''
1464
+ - id: model-160-vending-bench-2
1465
+ volatility: live
1466
+ url: https://andonlabs.com/evals/vending-bench-2
1467
+ fetch: http
1468
+ normaliser: text-default
1469
+ cited_regions:
1470
+ - id: rows
1471
+ locator:
1472
+ kind: page
1473
+ value: ''
1474
+
1475
+ # MODEL-118: pinned Open LLM Leaderboard result files; read 2026-09-25.
1476
+ - id: oll-v1-045da3eb1e87
1477
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/tiiuae/falcon-40b-instruct/results_2023-12-03T19-30-05.245215.json
1478
+ fetch: conditional_http
1479
+ normaliser: text-default
1480
+ cited_regions:
1481
+ - id: rows
1482
+ locator:
1483
+ kind: page
1484
+ value: ''
1485
+ - id: oll-v1-048e289b248c
1486
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-34B/results_2023-11-08T19-46-38.378007.json
1487
+ fetch: conditional_http
1488
+ normaliser: text-default
1489
+ cited_regions:
1490
+ - id: rows
1491
+ locator:
1492
+ kind: page
1493
+ value: ''
1494
+ - id: oll-v1-09bff549b797
1495
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/NousResearch/Hermes-2-Pro-Llama-3-8B/results_2024-05-02T09-00-48.637180.json
1496
+ fetch: conditional_http
1497
+ normaliser: text-default
1498
+ cited_regions:
1499
+ - id: rows
1500
+ locator:
1501
+ kind: page
1502
+ value: ''
1503
+ - id: oll-v1-0cdbc97e2f2e
1504
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/meta-llama/Llama-2-70b-chat-hf/results_2023-10-17T05-07-42.486452.json
1505
+ fetch: conditional_http
1506
+ normaliser: text-default
1507
+ cited_regions:
1508
+ - id: rows
1509
+ locator:
1510
+ kind: page
1511
+ value: ''
1512
+ - id: oll-v1-2404bc64c999
1513
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-1.5-34B-Chat-16K/results_2024-05-26T06-56-54.920335.json
1514
+ fetch: conditional_http
1515
+ normaliser: text-default
1516
+ cited_regions:
1517
+ - id: rows
1518
+ locator:
1519
+ kind: page
1520
+ value: ''
1521
+ - id: oll-v1-2b8faa8a1145
1522
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/google/gemma-2b/results_2024-02-22T14-01-00.018926.json
1523
+ fetch: conditional_http
1524
+ normaliser: text-default
1525
+ cited_regions:
1526
+ - id: rows
1527
+ locator:
1528
+ kind: page
1529
+ value: ''
1530
+ - id: oll-v1-2e0af8c86c8b
1531
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/microsoft/Phi-3-mini-128k-instruct/results_2024-04-25T11-04-08.300273.json
1532
+ fetch: conditional_http
1533
+ normaliser: text-default
1534
+ cited_regions:
1535
+ - id: rows
1536
+ locator:
1537
+ kind: page
1538
+ value: ''
1539
+ - id: oll-v1-3a39feefc6e7
1540
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/mistralai/Mistral-7B-Instruct-v0.1/results_2023-10-24T09-43-48.997990.json
1541
+ fetch: conditional_http
1542
+ normaliser: text-default
1543
+ cited_regions:
1544
+ - id: rows
1545
+ locator:
1546
+ kind: page
1547
+ value: ''
1548
+ - id: oll-v1-3b963c151fb1
1549
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-1.5-9B/results_2024-05-16T10-35-34.857914.json
1550
+ fetch: conditional_http
1551
+ normaliser: text-default
1552
+ cited_regions:
1553
+ - id: rows
1554
+ locator:
1555
+ kind: page
1556
+ value: ''
1557
+ - id: oll-v1-3f99042454a9
1558
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/NousResearch/Nous-Hermes-llama-2-7b/results_2023-10-22T01-50-03.524306.json
1559
+ fetch: conditional_http
1560
+ normaliser: text-default
1561
+ cited_regions:
1562
+ - id: rows
1563
+ locator:
1564
+ kind: page
1565
+ value: ''
1566
+ - id: oll-v1-412600e523b7
1567
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/tiiuae/falcon-40b/results_2023-11-27T10-24-56.579363.json
1568
+ fetch: conditional_http
1569
+ normaliser: text-default
1570
+ cited_regions:
1571
+ - id: rows
1572
+ locator:
1573
+ kind: page
1574
+ value: ''
1575
+ - id: oll-v1-4199875c7069
1576
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/meta-llama/Meta-Llama-3-8B/results_2024-05-28T19-40-23.721752.json
1577
+ fetch: conditional_http
1578
+ normaliser: text-default
1579
+ cited_regions:
1580
+ - id: rows
1581
+ locator:
1582
+ kind: page
1583
+ value: ''
1584
+ - id: oll-v1-459dba707d22
1585
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/mistralai/Mixtral-8x7B-Instruct-v0.1/results_2024-01-05T04-20-22.140239.json
1586
+ fetch: conditional_http
1587
+ normaliser: text-default
1588
+ cited_regions:
1589
+ - id: rows
1590
+ locator:
1591
+ kind: page
1592
+ value: ''
1593
+ - id: oll-v1-49d1fef96000
1594
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/meta-llama/Meta-Llama-3-70B-Instruct/results_2024-04-21T11-59-48.701689.json
1595
+ fetch: conditional_http
1596
+ normaliser: text-default
1597
+ cited_regions:
1598
+ - id: rows
1599
+ locator:
1600
+ kind: page
1601
+ value: ''
1602
+ - id: oll-v1-4b985ffc3a77
1603
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/meta-llama/Llama-2-7b-chat-hf/results_2023-10-15T02-34-15.484281.json
1604
+ fetch: conditional_http
1605
+ normaliser: text-default
1606
+ cited_regions:
1607
+ - id: rows
1608
+ locator:
1609
+ kind: page
1610
+ value: ''
1611
+ - id: oll-v1-4c6c85818b06
1612
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/microsoft/phi-2/results_2024-04-15T16-12-26.100927.json
1613
+ fetch: conditional_http
1614
+ normaliser: text-default
1615
+ cited_regions:
1616
+ - id: rows
1617
+ locator:
1618
+ kind: page
1619
+ value: ''
1620
+ - id: oll-v1-4e3abe9d8005
1621
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-1.5-9B-32K/results_2024-05-25T18-20-24.039645.json
1622
+ fetch: conditional_http
1623
+ normaliser: text-default
1624
+ cited_regions:
1625
+ - id: rows
1626
+ locator:
1627
+ kind: page
1628
+ value: ''
1629
+ - id: oll-v1-51fbae9d823c
1630
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/meta-llama/Meta-Llama-3-70B/results_2024-04-21T13-09-06.084236.json
1631
+ fetch: conditional_http
1632
+ normaliser: text-default
1633
+ cited_regions:
1634
+ - id: rows
1635
+ locator:
1636
+ kind: page
1637
+ value: ''
1638
+ - id: oll-v1-5790352933bd
1639
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-1.5-34B/results_2024-05-16T00-23-07.920103.json
1640
+ fetch: conditional_http
1641
+ normaliser: text-default
1642
+ cited_regions:
1643
+ - id: rows
1644
+ locator:
1645
+ kind: page
1646
+ value: ''
1647
+ - id: oll-v1-5a1fd131eab1
1648
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/NousResearch/Meta-Llama-3-8B-Instruct/results_2024-04-19T18-40-48.433302.json
1649
+ fetch: conditional_http
1650
+ normaliser: text-default
1651
+ cited_regions:
1652
+ - id: rows
1653
+ locator:
1654
+ kind: page
1655
+ value: ''
1656
+ - id: oll-v1-62f123b1e8cb
1657
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/NousResearch/Hermes-2-Theta-Llama-3-8B/results_2024-05-27T00-35-30.762626.json
1658
+ fetch: conditional_http
1659
+ normaliser: text-default
1660
+ cited_regions:
1661
+ - id: rows
1662
+ locator:
1663
+ kind: page
1664
+ value: ''
1665
+ - id: oll-v1-63b4ff14f40d
1666
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/deepseek-ai/deepseek-llm-7b-chat/results_2024-01-05T10-38-25.592014.json
1667
+ fetch: conditional_http
1668
+ normaliser: text-default
1669
+ cited_regions:
1670
+ - id: rows
1671
+ locator:
1672
+ kind: page
1673
+ value: ''
1674
+ - id: oll-v1-650475dc3cda
1675
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/deepseek-ai/deepseek-coder-6.7b-instruct/results_2024-01-05T09-40-26.509293.json
1676
+ fetch: conditional_http
1677
+ normaliser: text-default
1678
+ cited_regions:
1679
+ - id: rows
1680
+ locator:
1681
+ kind: page
1682
+ value: ''
1683
+ - id: oll-v1-6998cf83690a
1684
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/meta-llama/Llama-2-13b-hf/results_2023-12-02T13-11-49.394544.json
1685
+ fetch: conditional_http
1686
+ normaliser: text-default
1687
+ cited_regions:
1688
+ - id: rows
1689
+ locator:
1690
+ kind: page
1691
+ value: ''
1692
+ - id: oll-v1-6c31d09660ab
1693
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/allenai/OLMo-1B-hf/results_2024-04-23T06-24-47.411659.json
1694
+ fetch: conditional_http
1695
+ normaliser: text-default
1696
+ cited_regions:
1697
+ - id: rows
1698
+ locator:
1699
+ kind: page
1700
+ value: ''
1701
+ - id: oll-v1-7be10bea2c4f
1702
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-1.5-34B-32K/results_2024-05-26T07-04-09.158901.json
1703
+ fetch: conditional_http
1704
+ normaliser: text-default
1705
+ cited_regions:
1706
+ - id: rows
1707
+ locator:
1708
+ kind: page
1709
+ value: ''
1710
+ - id: oll-v1-7c13b2412d43
1711
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/baichuan-inc/Baichuan-7B/results_2023-09-22T17-53-01.811068.json
1712
+ fetch: conditional_http
1713
+ normaliser: text-default
1714
+ cited_regions:
1715
+ - id: rows
1716
+ locator:
1717
+ kind: page
1718
+ value: ''
1719
+ - id: oll-v1-7c5ceaa7fe1f
1720
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-1.5-34B-Chat/results_2024-05-15T03-44-20.662749.json
1721
+ fetch: conditional_http
1722
+ normaliser: text-default
1723
+ cited_regions:
1724
+ - id: rows
1725
+ locator:
1726
+ kind: page
1727
+ value: ''
1728
+ - id: oll-v1-86126911893f
1729
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/google/gemma-2b-it/results_2024-02-22T15-21-47.760131.json
1730
+ fetch: conditional_http
1731
+ normaliser: text-default
1732
+ cited_regions:
1733
+ - id: rows
1734
+ locator:
1735
+ kind: page
1736
+ value: ''
1737
+ - id: oll-v1-88acbaa3301e
1738
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-34B-200K/results_2024-04-16T04-20-00.686323.json
1739
+ fetch: conditional_http
1740
+ normaliser: text-default
1741
+ cited_regions:
1742
+ - id: rows
1743
+ locator:
1744
+ kind: page
1745
+ value: ''
1746
+ - id: oll-v1-8cb931b2eb81
1747
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-6B/results_2023-11-28T00-43-30.370535.json
1748
+ fetch: conditional_http
1749
+ normaliser: text-default
1750
+ cited_regions:
1751
+ - id: rows
1752
+ locator:
1753
+ kind: page
1754
+ value: ''
1755
+ - id: oll-v1-9ad51b3de802
1756
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/meta-llama/Meta-Llama-3-8B-Instruct/results_2024-04-19T09-19-13.454877.json
1757
+ fetch: conditional_http
1758
+ normaliser: text-default
1759
+ cited_regions:
1760
+ - id: rows
1761
+ locator:
1762
+ kind: page
1763
+ value: ''
1764
+ - id: oll-v1-9f07e96ec376
1765
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/mistralai/Mistral-7B-Instruct-v0.2/results_2023-12-12T03-37-50.599841.json
1766
+ fetch: conditional_http
1767
+ normaliser: text-default
1768
+ cited_regions:
1769
+ - id: rows
1770
+ locator:
1771
+ kind: page
1772
+ value: ''
1773
+ - id: oll-v1-a2db83d692a3
1774
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/tiiuae/falcon-11B/results_2024-05-10T12-57-08.635343.json
1775
+ fetch: conditional_http
1776
+ normaliser: text-default
1777
+ cited_regions:
1778
+ - id: rows
1779
+ locator:
1780
+ kind: page
1781
+ value: ''
1782
+ - id: oll-v1-a865328e0b66
1783
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/tiiuae/falcon-7b/results_2023-12-03T17-58-16.188347.json
1784
+ fetch: conditional_http
1785
+ normaliser: text-default
1786
+ cited_regions:
1787
+ - id: rows
1788
+ locator:
1789
+ kind: page
1790
+ value: ''
1791
+ - id: oll-v1-ae2fdf5972a8
1792
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-1.5-9B-Chat-16K/results_2024-05-25T18-33-08.508160.json
1793
+ fetch: conditional_http
1794
+ normaliser: text-default
1795
+ cited_regions:
1796
+ - id: rows
1797
+ locator:
1798
+ kind: page
1799
+ value: ''
1800
+ - id: oll-v1-b37720c251e3
1801
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/tiiuae/falcon-7b-instruct/results_2023-12-03T18-01-45.204079.json
1802
+ fetch: conditional_http
1803
+ normaliser: text-default
1804
+ cited_regions:
1805
+ - id: rows
1806
+ locator:
1807
+ kind: page
1808
+ value: ''
1809
+ - id: oll-v1-b411691a236c
1810
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/deepseek-ai/deepseek-coder-6.7b-base/results_2024-04-02T21-41-57.054032.json
1811
+ fetch: conditional_http
1812
+ normaliser: text-default
1813
+ cited_regions:
1814
+ - id: rows
1815
+ locator:
1816
+ kind: page
1817
+ value: ''
1818
+ - id: oll-v1-b5acec34f2b5
1819
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/meta-llama/Llama-2-7b-hf/results_2023-12-02T13-00-54.924067.json
1820
+ fetch: conditional_http
1821
+ normaliser: text-default
1822
+ cited_regions:
1823
+ - id: rows
1824
+ locator:
1825
+ kind: page
1826
+ value: ''
1827
+ - id: oll-v1-c788c8cc0fc3
1828
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-34B-Chat/results_2023-12-05T03-47-25.491369.json
1829
+ fetch: conditional_http
1830
+ normaliser: text-default
1831
+ cited_regions:
1832
+ - id: rows
1833
+ locator:
1834
+ kind: page
1835
+ value: ''
1836
+ - id: oll-v1-ce2acb9af1e8
1837
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-9B/results_2024-03-07T00-53-16.402231.json
1838
+ fetch: conditional_http
1839
+ normaliser: text-default
1840
+ cited_regions:
1841
+ - id: rows
1842
+ locator:
1843
+ kind: page
1844
+ value: ''
1845
+ - id: oll-v1-d07c35ac3594
1846
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/meta-llama/Llama-2-70b-hf/results_2023-12-03T01-14-42.713769.json
1847
+ fetch: conditional_http
1848
+ normaliser: text-default
1849
+ cited_regions:
1850
+ - id: rows
1851
+ locator:
1852
+ kind: page
1853
+ value: ''
1854
+ - id: oll-v1-d29b3d579be8
1855
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/meta-llama/Llama-2-13b-chat-hf/results_2023-10-14T19-39-26.636545.json
1856
+ fetch: conditional_http
1857
+ normaliser: text-default
1858
+ cited_regions:
1859
+ - id: rows
1860
+ locator:
1861
+ kind: page
1862
+ value: ''
1863
+ - id: oll-v1-d4b04a77b077
1864
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/NousResearch/Nous-Hermes-2-SOLAR-10.7B/results_2024-01-04T13-44-46.879799.json
1865
+ fetch: conditional_http
1866
+ normaliser: text-default
1867
+ cited_regions:
1868
+ - id: rows
1869
+ locator:
1870
+ kind: page
1871
+ value: ''
1872
+ - id: oll-v1-d68a66649f8d
1873
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-1.5-6B/results_2024-05-30T17-21-52.581058.json
1874
+ fetch: conditional_http
1875
+ normaliser: text-default
1876
+ cited_regions:
1877
+ - id: rows
1878
+ locator:
1879
+ kind: page
1880
+ value: ''
1881
+ - id: oll-v1-e21c0e7ff1d6
1882
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/NousResearch/Nous-Hermes-2-Yi-34B/results_2023-12-29T16-55-23.292289.json
1883
+ fetch: conditional_http
1884
+ normaliser: text-default
1885
+ cited_regions:
1886
+ - id: rows
1887
+ locator:
1888
+ kind: page
1889
+ value: ''
1890
+ - id: oll-v1-e476ebcdb70d
1891
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO/results_2024-01-22T17-09-50.643842.json
1892
+ fetch: conditional_http
1893
+ normaliser: text-default
1894
+ cited_regions:
1895
+ - id: rows
1896
+ locator:
1897
+ kind: page
1898
+ value: ''
1899
+ - id: oll-v1-e8b8eee41571
1900
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/microsoft/Phi-3-mini-4k-instruct/results_2024-04-25T13-30-16.480959.json
1901
+ fetch: conditional_http
1902
+ normaliser: text-default
1903
+ cited_regions:
1904
+ - id: rows
1905
+ locator:
1906
+ kind: page
1907
+ value: ''
1908
+ - id: oll-v1-ea341b772aad
1909
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-6B-200K/results_2023-12-02T12-58-15.129366.json
1910
+ fetch: conditional_http
1911
+ normaliser: text-default
1912
+ cited_regions:
1913
+ - id: rows
1914
+ locator:
1915
+ kind: page
1916
+ value: ''
1917
+ - id: oll-v1-ef18dcc4683c
1918
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-1.5-9B-Chat/results_2024-05-16T05-38-57.460156.json
1919
+ fetch: conditional_http
1920
+ normaliser: text-default
1921
+ cited_regions:
1922
+ - id: rows
1923
+ locator:
1924
+ kind: page
1925
+ value: ''
1926
+ - id: oll-v1-f056592ff29d
1927
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/mistralai/Mixtral-8x22B-Instruct-v0.1/results_2024-04-18T04-27-50.095241.json
1928
+ fetch: conditional_http
1929
+ normaliser: text-default
1930
+ cited_regions:
1931
+ - id: rows
1932
+ locator:
1933
+ kind: page
1934
+ value: ''
1935
+ - id: oll-v1-f4ce6c6fb60f
1936
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/01-ai/Yi-1.5-6B-Chat/results_2024-05-16T14-12-12.578596.json
1937
+ fetch: conditional_http
1938
+ normaliser: text-default
1939
+ cited_regions:
1940
+ - id: rows
1941
+ locator:
1942
+ kind: page
1943
+ value: ''
1944
+ - id: oll-v1-f4f35ac5027b
1945
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/mistralai/Mixtral-8x7B-v0.1/results_2024-01-04T16-34-48.985318.json
1946
+ fetch: conditional_http
1947
+ normaliser: text-default
1948
+ cited_regions:
1949
+ - id: rows
1950
+ locator:
1951
+ kind: page
1952
+ value: ''
1953
+ - id: oll-v1-fef176383565
1954
+ url: https://huggingface.co/datasets/open-llm-leaderboard-old/results/resolve/23474373f8874f9057d23b97e5a41e911d2721c5/mistralai/Mistral-7B-v0.1/results_2023-12-02T13-02-14.153054.json
1955
+ fetch: conditional_http
1956
+ normaliser: text-default
1957
+ cited_regions:
1958
+ - id: rows
1959
+ locator:
1960
+ kind: page
1961
+ value: ''
1962
+ - id: oll-v2-022a5eb83f36
1963
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/tiiuae/Falcon3-1B-Base/results_2025-02-13T18-27-04.338360.json
1964
+ fetch: conditional_http
1965
+ normaliser: text-default
1966
+ cited_regions:
1967
+ - id: rows
1968
+ locator:
1969
+ kind: page
1970
+ value: ''
1971
+ - id: oll-v2-0435d7c7017e
1972
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/NousResearch/Hermes-3-Llama-3.2-3B/results_2025-02-13T18-27-04.338360.json
1973
+ fetch: conditional_http
1974
+ normaliser: text-default
1975
+ cited_regions:
1976
+ - id: rows
1977
+ locator:
1978
+ kind: page
1979
+ value: ''
1980
+ - id: oll-v2-0589baed3667
1981
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/togethercomputer/LLaMA-2-7B-32K/results_2025-02-13T18-27-04.338360.json
1982
+ fetch: conditional_http
1983
+ normaliser: text-default
1984
+ cited_regions:
1985
+ - id: rows
1986
+ locator:
1987
+ kind: page
1988
+ value: ''
1989
+ - id: oll-v2-10ac5516f60b
1990
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/gemma-2b-it/results_2025-02-13T18-27-04.338360.json
1991
+ fetch: conditional_http
1992
+ normaliser: text-default
1993
+ cited_regions:
1994
+ - id: rows
1995
+ locator:
1996
+ kind: page
1997
+ value: ''
1998
+ - id: oll-v2-10d6931f1023
1999
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/NousResearch/Nous-Hermes-2-SOLAR-10.7B/results_2025-02-13T18-27-04.338360.json
2000
+ fetch: conditional_http
2001
+ normaliser: text-default
2002
+ cited_regions:
2003
+ - id: rows
2004
+ locator:
2005
+ kind: page
2006
+ value: ''
2007
+ - id: oll-v2-127320e0dfc7
2008
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/togethercomputer/RedPajama-INCITE-Base-3B-v1/results_2025-02-13T18-27-04.338360.json
2009
+ fetch: conditional_http
2010
+ normaliser: text-default
2011
+ cited_regions:
2012
+ - id: rows
2013
+ locator:
2014
+ kind: page
2015
+ value: ''
2016
+ - id: oll-v2-136769cb5ced
2017
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/RWKV/rwkv-raven-14b/results_2025-02-13T18-27-04.338360.json
2018
+ fetch: conditional_http
2019
+ normaliser: text-default
2020
+ cited_regions:
2021
+ - id: rows
2022
+ locator:
2023
+ kind: page
2024
+ value: ''
2025
+ - id: oll-v2-153991bc92af
2026
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/teknium/OpenHermes-2.5-Mistral-7B/results_2025-02-13T18-27-04.338360.json
2027
+ fetch: conditional_http
2028
+ normaliser: text-default
2029
+ cited_regions:
2030
+ - id: rows
2031
+ locator:
2032
+ kind: page
2033
+ value: ''
2034
+ - id: oll-v2-16b7b22edf8d
2035
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/mistralai/Mixtral-8x22B-v0.1/results_2025-02-13T18-27-04.338360.json
2036
+ fetch: conditional_http
2037
+ normaliser: text-default
2038
+ cited_regions:
2039
+ - id: rows
2040
+ locator:
2041
+ kind: page
2042
+ value: ''
2043
+ - id: oll-v2-18606e317e6f
2044
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/tiiuae/falcon-40b/results_2025-02-13T18-27-04.338360.json
2045
+ fetch: conditional_http
2046
+ normaliser: text-default
2047
+ cited_regions:
2048
+ - id: rows
2049
+ locator:
2050
+ kind: page
2051
+ value: ''
2052
+ - id: oll-v2-1a7576e9b9a3
2053
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/Qwen/Qwen2.5-Coder-7B-Instruct/results_2024-11-07T03-51-21.119041.json
2054
+ fetch: conditional_http
2055
+ normaliser: text-default
2056
+ cited_regions:
2057
+ - id: rows
2058
+ locator:
2059
+ kind: page
2060
+ value: ''
2061
+ - id: oll-v2-2058284a7643
2062
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/stabilityai/stablelm-zephyr-3b/results_2025-02-13T18-27-04.338360.json
2063
+ fetch: conditional_http
2064
+ normaliser: text-default
2065
+ cited_regions:
2066
+ - id: rows
2067
+ locator:
2068
+ kind: page
2069
+ value: ''
2070
+ - id: oll-v2-2440b37b7637
2071
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/tiiuae/Falcon3-Mamba-7B-Instruct/results_2025-02-13T18-27-04.338360.json
2072
+ fetch: conditional_http
2073
+ normaliser: text-default
2074
+ cited_regions:
2075
+ - id: rows
2076
+ locator:
2077
+ kind: page
2078
+ value: ''
2079
+ - id: oll-v2-24bf0e9199ab
2080
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/deepseek-ai/deepseek-llm-7b-base/results_2025-02-13T18-27-04.338360.json
2081
+ fetch: conditional_http
2082
+ normaliser: text-default
2083
+ cited_regions:
2084
+ - id: rows
2085
+ locator:
2086
+ kind: page
2087
+ value: ''
2088
+ - id: oll-v2-257576f61eeb
2089
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/results_2025-02-13T18-27-04.338360.json
2090
+ fetch: conditional_http
2091
+ normaliser: text-default
2092
+ cited_regions:
2093
+ - id: rows
2094
+ locator:
2095
+ kind: page
2096
+ value: ''
2097
+ - id: oll-v2-261ff26b1a6c
2098
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/ibm-granite/granite-3.0-8b-instruct/results_2025-02-13T18-27-04.338360.json
2099
+ fetch: conditional_http
2100
+ normaliser: text-default
2101
+ cited_regions:
2102
+ - id: rows
2103
+ locator:
2104
+ kind: page
2105
+ value: ''
2106
+ - id: oll-v2-299b7321e950
2107
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Meta-Llama-3-70B-Instruct/results_2025-02-13T18-27-04.338360.json
2108
+ fetch: conditional_http
2109
+ normaliser: text-default
2110
+ cited_regions:
2111
+ - id: rows
2112
+ locator:
2113
+ kind: page
2114
+ value: ''
2115
+ - id: oll-v2-2acf8c9b85dc
2116
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/ibm-granite/granite-3.0-1b-a400m-base/results_2025-02-13T18-27-04.338360.json
2117
+ fetch: conditional_http
2118
+ normaliser: text-default
2119
+ cited_regions:
2120
+ - id: rows
2121
+ locator:
2122
+ kind: page
2123
+ value: ''
2124
+ - id: oll-v2-2bb3be6cc94e
2125
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Meta-Llama-3-8B-Instruct/results_2025-02-13T18-27-04.338360.json
2126
+ fetch: conditional_http
2127
+ normaliser: text-default
2128
+ cited_regions:
2129
+ - id: rows
2130
+ locator:
2131
+ kind: page
2132
+ value: ''
2133
+ - id: oll-v2-2c9dabc42838
2134
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/Qwen/Qwen2.5-0.5B-Instruct/results_2025-02-13T18-27-04.338360.json
2135
+ fetch: conditional_http
2136
+ normaliser: text-default
2137
+ cited_regions:
2138
+ - id: rows
2139
+ locator:
2140
+ kind: page
2141
+ value: ''
2142
+ - id: oll-v2-33977bd3d90f
2143
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/tiiuae/Falcon3-3B-Base/results_2025-02-13T18-27-04.338360.json
2144
+ fetch: conditional_http
2145
+ normaliser: text-default
2146
+ cited_regions:
2147
+ - id: rows
2148
+ locator:
2149
+ kind: page
2150
+ value: ''
2151
+ - id: oll-v2-37fe6bc5cb2e
2152
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/tiiuae/Falcon3-1B-Instruct/results_2025-02-13T18-27-04.338360.json
2153
+ fetch: conditional_http
2154
+ normaliser: text-default
2155
+ cited_regions:
2156
+ - id: rows
2157
+ locator:
2158
+ kind: page
2159
+ value: ''
2160
+ - id: oll-v2-3a2971acf094
2161
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/stabilityai/stablelm-3b-4e1t/results_2025-02-13T18-27-04.338360.json
2162
+ fetch: conditional_http
2163
+ normaliser: text-default
2164
+ cited_regions:
2165
+ - id: rows
2166
+ locator:
2167
+ kind: page
2168
+ value: ''
2169
+ - id: oll-v2-3ccdc72560df
2170
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/mt5-base/results_2025-02-13T18-27-04.338360.json
2171
+ fetch: conditional_http
2172
+ normaliser: text-default
2173
+ cited_regions:
2174
+ - id: rows
2175
+ locator:
2176
+ kind: page
2177
+ value: ''
2178
+ - id: oll-v2-3e4bd774f18c
2179
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/ibm-granite/granite-3.1-1b-a400m-instruct/results_2025-02-13T18-27-04.338360.json
2180
+ fetch: conditional_http
2181
+ normaliser: text-default
2182
+ cited_regions:
2183
+ - id: rows
2184
+ locator:
2185
+ kind: page
2186
+ value: ''
2187
+ - id: oll-v2-406ddda96121
2188
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/deepseek-ai/deepseek-moe-16b-base/results_2025-02-13T18-27-04.338360.json
2189
+ fetch: conditional_http
2190
+ normaliser: text-default
2191
+ cited_regions:
2192
+ - id: rows
2193
+ locator:
2194
+ kind: page
2195
+ value: ''
2196
+ - id: oll-v2-41b051f264a1
2197
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/flan-t5-small/results_2025-02-13T18-27-04.338360.json
2198
+ fetch: conditional_http
2199
+ normaliser: text-default
2200
+ cited_regions:
2201
+ - id: rows
2202
+ locator:
2203
+ kind: page
2204
+ value: ''
2205
+ - id: oll-v2-423a5645182d
2206
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/mt5-small/results_2025-02-13T18-27-04.338360.json
2207
+ fetch: conditional_http
2208
+ normaliser: text-default
2209
+ cited_regions:
2210
+ - id: rows
2211
+ locator:
2212
+ kind: page
2213
+ value: ''
2214
+ - id: oll-v2-43ca456ad2df
2215
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-34B-200K/results_2025-02-13T18-27-04.338360.json
2216
+ fetch: conditional_http
2217
+ normaliser: text-default
2218
+ cited_regions:
2219
+ - id: rows
2220
+ locator:
2221
+ kind: page
2222
+ value: ''
2223
+ - id: oll-v2-46e0a09eb840
2224
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/togethercomputer/GPT-JT-6B-v1/results_2025-02-13T18-27-04.338360.json
2225
+ fetch: conditional_http
2226
+ normaliser: text-default
2227
+ cited_regions:
2228
+ - id: rows
2229
+ locator:
2230
+ kind: page
2231
+ value: ''
2232
+ - id: oll-v2-488a156533d7
2233
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/ibm-granite/granite-3.1-8b-instruct/results_2025-02-13T18-27-04.338360.json
2234
+ fetch: conditional_http
2235
+ normaliser: text-default
2236
+ cited_regions:
2237
+ - id: rows
2238
+ locator:
2239
+ kind: page
2240
+ value: ''
2241
+ - id: oll-v2-49c8b0f3e4e3
2242
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/flan-t5-large/results_2025-02-13T18-27-04.338360.json
2243
+ fetch: conditional_http
2244
+ normaliser: text-default
2245
+ cited_regions:
2246
+ - id: rows
2247
+ locator:
2248
+ kind: page
2249
+ value: ''
2250
+ - id: oll-v2-4bd4d8c7144a
2251
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/mistralai/Mixtral-8x7B-Instruct-v0.1/results_2025-02-13T18-27-04.338360.json
2252
+ fetch: conditional_http
2253
+ normaliser: text-default
2254
+ cited_regions:
2255
+ - id: rows
2256
+ locator:
2257
+ kind: page
2258
+ value: ''
2259
+ - id: oll-v2-4c35de886219
2260
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-9B-200K/results_2025-02-13T18-27-04.338360.json
2261
+ fetch: conditional_http
2262
+ normaliser: text-default
2263
+ cited_regions:
2264
+ - id: rows
2265
+ locator:
2266
+ kind: page
2267
+ value: ''
2268
+ - id: oll-v2-4c6acb749a24
2269
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Llama-2-7b-hf/results_2025-02-13T18-27-04.338360.json
2270
+ fetch: conditional_http
2271
+ normaliser: text-default
2272
+ cited_regions:
2273
+ - id: rows
2274
+ locator:
2275
+ kind: page
2276
+ value: ''
2277
+ - id: oll-v2-4d4b253cabb9
2278
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/tiiuae/falcon-11B/results_2025-02-13T18-27-04.338360.json
2279
+ fetch: conditional_http
2280
+ normaliser: text-default
2281
+ cited_regions:
2282
+ - id: rows
2283
+ locator:
2284
+ kind: page
2285
+ value: ''
2286
+ - id: oll-v2-4dd33d2a867b
2287
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/deepseek-ai/deepseek-llm-7b-chat/results_2025-02-13T18-27-04.338360.json
2288
+ fetch: conditional_http
2289
+ normaliser: text-default
2290
+ cited_regions:
2291
+ - id: rows
2292
+ locator:
2293
+ kind: page
2294
+ value: ''
2295
+ - id: oll-v2-528d401e9900
2296
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/Qwen/Qwen2.5-Coder-7B-Instruct/results_2025-02-13T18-27-04.338360.json
2297
+ fetch: conditional_http
2298
+ normaliser: text-default
2299
+ cited_regions:
2300
+ - id: rows
2301
+ locator:
2302
+ kind: page
2303
+ value: ''
2304
+ - id: oll-v2-52be3422a196
2305
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-9B/results_2025-02-13T18-27-04.338360.json
2306
+ fetch: conditional_http
2307
+ normaliser: text-default
2308
+ cited_regions:
2309
+ - id: rows
2310
+ locator:
2311
+ kind: page
2312
+ value: ''
2313
+ - id: oll-v2-56fd238af478
2314
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Llama-2-70b-hf/results_2025-02-13T18-27-04.338360.json
2315
+ fetch: conditional_http
2316
+ normaliser: text-default
2317
+ cited_regions:
2318
+ - id: rows
2319
+ locator:
2320
+ kind: page
2321
+ value: ''
2322
+ - id: oll-v2-591313014365
2323
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/togethercomputer/RedPajama-INCITE-7B-Chat/results_2025-02-13T18-27-04.338360.json
2324
+ fetch: conditional_http
2325
+ normaliser: text-default
2326
+ cited_regions:
2327
+ - id: rows
2328
+ locator:
2329
+ kind: page
2330
+ value: ''
2331
+ - id: oll-v2-5a02359c436a
2332
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/gemma-2b/results_2025-02-13T18-27-04.338360.json
2333
+ fetch: conditional_http
2334
+ normaliser: text-default
2335
+ cited_regions:
2336
+ - id: rows
2337
+ locator:
2338
+ kind: page
2339
+ value: ''
2340
+ - id: oll-v2-5c0a6e0ea9dd
2341
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/mistralai/Mixtral-8x7B-v0.1/results_2025-02-13T18-27-04.338360.json
2342
+ fetch: conditional_http
2343
+ normaliser: text-default
2344
+ cited_regions:
2345
+ - id: rows
2346
+ locator:
2347
+ kind: page
2348
+ value: ''
2349
+ - id: oll-v2-5d1058d8498d
2350
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-1.5-9B-Chat/results_2025-02-13T18-27-04.338360.json
2351
+ fetch: conditional_http
2352
+ normaliser: text-default
2353
+ cited_regions:
2354
+ - id: rows
2355
+ locator:
2356
+ kind: page
2357
+ value: ''
2358
+ - id: oll-v2-5eab82af5137
2359
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-6B/results_2025-02-13T18-27-04.338360.json
2360
+ fetch: conditional_http
2361
+ normaliser: text-default
2362
+ cited_regions:
2363
+ - id: rows
2364
+ locator:
2365
+ kind: page
2366
+ value: ''
2367
+ - id: oll-v2-5eb856752837
2368
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/gemma-2b/results_2024-10-24T00-00-00.000000.json
2369
+ fetch: conditional_http
2370
+ normaliser: text-default
2371
+ cited_regions:
2372
+ - id: rows
2373
+ locator:
2374
+ kind: page
2375
+ value: ''
2376
+ - id: oll-v2-5fcacecfba75
2377
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/allenai/OLMo-1B-hf/results_2025-02-13T18-27-04.338360.json
2378
+ fetch: conditional_http
2379
+ normaliser: text-default
2380
+ cited_regions:
2381
+ - id: rows
2382
+ locator:
2383
+ kind: page
2384
+ value: ''
2385
+ - id: oll-v2-608aec7d7e62
2386
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/ibm-granite/granite-3.1-2b-instruct/results_2025-02-13T18-27-04.338360.json
2387
+ fetch: conditional_http
2388
+ normaliser: text-default
2389
+ cited_regions:
2390
+ - id: rows
2391
+ locator:
2392
+ kind: page
2393
+ value: ''
2394
+ - id: oll-v2-621f5965c74f
2395
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-34B/results_2025-02-13T18-27-04.338360.json
2396
+ fetch: conditional_http
2397
+ normaliser: text-default
2398
+ cited_regions:
2399
+ - id: rows
2400
+ locator:
2401
+ kind: page
2402
+ value: ''
2403
+ - id: oll-v2-631c76e81143
2404
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-34B-Chat/results_2025-02-13T18-27-04.338360.json
2405
+ fetch: conditional_http
2406
+ normaliser: text-default
2407
+ cited_regions:
2408
+ - id: rows
2409
+ locator:
2410
+ kind: page
2411
+ value: ''
2412
+ - id: oll-v2-64afe26e8540
2413
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/NousResearch/Hermes-2-Theta-Llama-3-8B/results_2025-02-13T18-27-04.338360.json
2414
+ fetch: conditional_http
2415
+ normaliser: text-default
2416
+ cited_regions:
2417
+ - id: rows
2418
+ locator:
2419
+ kind: page
2420
+ value: ''
2421
+ - id: oll-v2-6618c8e8af38
2422
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/togethercomputer/GPT-NeoXT-Chat-Base-20B/results_2025-02-13T18-27-04.338360.json
2423
+ fetch: conditional_http
2424
+ normaliser: text-default
2425
+ cited_regions:
2426
+ - id: rows
2427
+ locator:
2428
+ kind: page
2429
+ value: ''
2430
+ - id: oll-v2-6c0337986cee
2431
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8B/results_2025-02-13T18-27-04.338360.json
2432
+ fetch: conditional_http
2433
+ normaliser: text-default
2434
+ cited_regions:
2435
+ - id: rows
2436
+ locator:
2437
+ kind: page
2438
+ value: ''
2439
+ - id: oll-v2-6d892166e3fe
2440
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-1.5-9B-32K/results_2025-02-13T18-27-04.338360.json
2441
+ fetch: conditional_http
2442
+ normaliser: text-default
2443
+ cited_regions:
2444
+ - id: rows
2445
+ locator:
2446
+ kind: page
2447
+ value: ''
2448
+ - id: oll-v2-6ef17e8f08b8
2449
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-1.5-34B-32K/results_2025-02-13T18-27-04.338360.json
2450
+ fetch: conditional_http
2451
+ normaliser: text-default
2452
+ cited_regions:
2453
+ - id: rows
2454
+ locator:
2455
+ kind: page
2456
+ value: ''
2457
+ - id: oll-v2-708ef66d9078
2458
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/NousResearch/Nous-Hermes-llama-2-7b/results_2025-02-13T18-27-04.338360.json
2459
+ fetch: conditional_http
2460
+ normaliser: text-default
2461
+ cited_regions:
2462
+ - id: rows
2463
+ locator:
2464
+ kind: page
2465
+ value: ''
2466
+ - id: oll-v2-712d08436bfb
2467
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/togethercomputer/RedPajama-INCITE-7B-Base/results_2025-02-13T18-27-04.338360.json
2468
+ fetch: conditional_http
2469
+ normaliser: text-default
2470
+ cited_regions:
2471
+ - id: rows
2472
+ locator:
2473
+ kind: page
2474
+ value: ''
2475
+ - id: oll-v2-71cc8bcbe701
2476
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/flan-t5-xl/results_2024-10-24T00-00-00.000000.json
2477
+ fetch: conditional_http
2478
+ normaliser: text-default
2479
+ cited_regions:
2480
+ - id: rows
2481
+ locator:
2482
+ kind: page
2483
+ value: ''
2484
+ - id: oll-v2-73654f57858e
2485
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/tiiuae/Falcon3-7B-Base/results_2025-02-13T18-27-04.338360.json
2486
+ fetch: conditional_http
2487
+ normaliser: text-default
2488
+ cited_regions:
2489
+ - id: rows
2490
+ locator:
2491
+ kind: page
2492
+ value: ''
2493
+ - id: oll-v2-7375a1bb4069
2494
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/BAAI/Infinity-Instruct-3M-0625-Llama3-8B/results_2025-02-13T18-27-04.338360.json
2495
+ fetch: conditional_http
2496
+ normaliser: text-default
2497
+ cited_regions:
2498
+ - id: rows
2499
+ locator:
2500
+ kind: page
2501
+ value: ''
2502
+ - id: oll-v2-73918124b466
2503
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/microsoft/Phi-3.5-mini-instruct/results_2025-02-13T18-27-04.338360.json
2504
+ fetch: conditional_http
2505
+ normaliser: text-default
2506
+ cited_regions:
2507
+ - id: rows
2508
+ locator:
2509
+ kind: page
2510
+ value: ''
2511
+ - id: oll-v2-74e349ea7cb8
2512
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/togethercomputer/RedPajama-INCITE-Chat-3B-v1/results_2025-02-13T18-27-04.338360.json
2513
+ fetch: conditional_http
2514
+ normaliser: text-default
2515
+ cited_regions:
2516
+ - id: rows
2517
+ locator:
2518
+ kind: page
2519
+ value: ''
2520
+ - id: oll-v2-75e7f5ee9805
2521
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/Qwen/Qwen2.5-Coder-32B-Instruct/results_2025-02-13T18-27-04.338360.json
2522
+ fetch: conditional_http
2523
+ normaliser: text-default
2524
+ cited_regions:
2525
+ - id: rows
2526
+ locator:
2527
+ kind: page
2528
+ value: ''
2529
+ - id: oll-v2-7745ba9849a8
2530
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/Qwen/Qwen2.5-Coder-14B-Instruct/results_2025-02-13T18-27-04.338360.json
2531
+ fetch: conditional_http
2532
+ normaliser: text-default
2533
+ cited_regions:
2534
+ - id: rows
2535
+ locator:
2536
+ kind: page
2537
+ value: ''
2538
+ - id: oll-v2-79e7a676234c
2539
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Llama-3.2-1B/results_2025-02-13T18-27-04.338360.json
2540
+ fetch: conditional_http
2541
+ normaliser: text-default
2542
+ cited_regions:
2543
+ - id: rows
2544
+ locator:
2545
+ kind: page
2546
+ value: ''
2547
+ - id: oll-v2-878fe1d5dc11
2548
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/microsoft/Phi-3-mini-4k-instruct/results_2024-06-17T11-04-33.850464.json
2549
+ fetch: conditional_http
2550
+ normaliser: text-default
2551
+ cited_regions:
2552
+ - id: rows
2553
+ locator:
2554
+ kind: page
2555
+ value: ''
2556
+ - id: oll-v2-87b55551f5f6
2557
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/tiiuae/falcon-40b-instruct/results_2025-02-13T18-27-04.338360.json
2558
+ fetch: conditional_http
2559
+ normaliser: text-default
2560
+ cited_regions:
2561
+ - id: rows
2562
+ locator:
2563
+ kind: page
2564
+ value: ''
2565
+ - id: oll-v2-881add5abb33
2566
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO/results_2025-02-13T18-27-04.338360.json
2567
+ fetch: conditional_http
2568
+ normaliser: text-default
2569
+ cited_regions:
2570
+ - id: rows
2571
+ locator:
2572
+ kind: page
2573
+ value: ''
2574
+ - id: oll-v2-88e9c32f0b4f
2575
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-6B-Chat/results_2025-02-13T18-27-04.338360.json
2576
+ fetch: conditional_http
2577
+ normaliser: text-default
2578
+ cited_regions:
2579
+ - id: rows
2580
+ locator:
2581
+ kind: page
2582
+ value: ''
2583
+ - id: oll-v2-8ac0464c73b8
2584
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/flan-t5-base/results_2025-02-13T18-27-04.338360.json
2585
+ fetch: conditional_http
2586
+ normaliser: text-default
2587
+ cited_regions:
2588
+ - id: rows
2589
+ locator:
2590
+ kind: page
2591
+ value: ''
2592
+ - id: oll-v2-8c1538d4a058
2593
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/Qwen/Qwen2.5-1.5B-Instruct/results_2025-02-13T18-27-04.338360.json
2594
+ fetch: conditional_http
2595
+ normaliser: text-default
2596
+ cited_regions:
2597
+ - id: rows
2598
+ locator:
2599
+ kind: page
2600
+ value: ''
2601
+ - id: oll-v2-8c644ad8ecb3
2602
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/tiiuae/Falcon3-3B-Instruct/results_2025-02-13T18-27-04.338360.json
2603
+ fetch: conditional_http
2604
+ normaliser: text-default
2605
+ cited_regions:
2606
+ - id: rows
2607
+ locator:
2608
+ kind: page
2609
+ value: ''
2610
+ - id: oll-v2-8e4c95a5dc99
2611
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/mistralai/Mistral-7B-Instruct-v0.2/results_2025-02-13T18-27-04.338360.json
2612
+ fetch: conditional_http
2613
+ normaliser: text-default
2614
+ cited_regions:
2615
+ - id: rows
2616
+ locator:
2617
+ kind: page
2618
+ value: ''
2619
+ - id: oll-v2-8fee2c3f372b
2620
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/mistralai/Mixtral-8x22B-Instruct-v0.1/results_2024-06-26T15-18-07.434042.json
2621
+ fetch: conditional_http
2622
+ normaliser: text-default
2623
+ cited_regions:
2624
+ - id: rows
2625
+ locator:
2626
+ kind: page
2627
+ value: ''
2628
+ - id: oll-v2-9111785434bf
2629
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/microsoft/phi-2/results_2025-02-13T18-27-04.338360.json
2630
+ fetch: conditional_http
2631
+ normaliser: text-default
2632
+ cited_regions:
2633
+ - id: rows
2634
+ locator:
2635
+ kind: page
2636
+ value: ''
2637
+ - id: oll-v2-9ac29aae4cee
2638
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/mistralai/Mistral-7B-Instruct-v0.1/results_2025-02-13T18-27-04.338360.json
2639
+ fetch: conditional_http
2640
+ normaliser: text-default
2641
+ cited_regions:
2642
+ - id: rows
2643
+ locator:
2644
+ kind: page
2645
+ value: ''
2646
+ - id: oll-v2-9c7075604dc5
2647
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-1.5-34B-Chat/results_2025-02-13T18-27-04.338360.json
2648
+ fetch: conditional_http
2649
+ normaliser: text-default
2650
+ cited_regions:
2651
+ - id: rows
2652
+ locator:
2653
+ kind: page
2654
+ value: ''
2655
+ - id: oll-v2-9ec632238071
2656
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/mistralai/Mistral-7B-Instruct-v0.3/results_2025-02-13T18-27-04.338360.json
2657
+ fetch: conditional_http
2658
+ normaliser: text-default
2659
+ cited_regions:
2660
+ - id: rows
2661
+ locator:
2662
+ kind: page
2663
+ value: ''
2664
+ - id: oll-v2-9ee9bcbff73b
2665
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/gemma-2-2b/results_2025-02-13T18-27-04.338360.json
2666
+ fetch: conditional_http
2667
+ normaliser: text-default
2668
+ cited_regions:
2669
+ - id: rows
2670
+ locator:
2671
+ kind: page
2672
+ value: ''
2673
+ - id: oll-v2-a0d4a4c34cdb
2674
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/togethercomputer/RedPajama-INCITE-7B-Instruct/results_2025-02-13T18-27-04.338360.json
2675
+ fetch: conditional_http
2676
+ normaliser: text-default
2677
+ cited_regions:
2678
+ - id: rows
2679
+ locator:
2680
+ kind: page
2681
+ value: ''
2682
+ - id: oll-v2-a125e4bb5978
2683
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/microsoft/DialoGPT-medium/results_2025-02-13T18-27-04.338360.json
2684
+ fetch: conditional_http
2685
+ normaliser: text-default
2686
+ cited_regions:
2687
+ - id: rows
2688
+ locator:
2689
+ kind: page
2690
+ value: ''
2691
+ - id: oll-v2-a3fc9fde34b9
2692
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/ai21labs/Jamba-v0.1/results_2025-02-13T18-27-04.338360.json
2693
+ fetch: conditional_http
2694
+ normaliser: text-default
2695
+ cited_regions:
2696
+ - id: rows
2697
+ locator:
2698
+ kind: page
2699
+ value: ''
2700
+ - id: oll-v2-a9310e2c6868
2701
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Llama-3.2-3B/results_2025-02-13T18-27-04.338360.json
2702
+ fetch: conditional_http
2703
+ normaliser: text-default
2704
+ cited_regions:
2705
+ - id: rows
2706
+ locator:
2707
+ kind: page
2708
+ value: ''
2709
+ - id: oll-v2-a96fec9a4280
2710
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-1.5-9B-Chat-16K/results_2025-02-13T18-27-04.338360.json
2711
+ fetch: conditional_http
2712
+ normaliser: text-default
2713
+ cited_regions:
2714
+ - id: rows
2715
+ locator:
2716
+ kind: page
2717
+ value: ''
2718
+ - id: oll-v2-a9a1fae4b235
2719
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-1.5-9B/results_2025-02-13T18-27-04.338360.json
2720
+ fetch: conditional_http
2721
+ normaliser: text-default
2722
+ cited_regions:
2723
+ - id: rows
2724
+ locator:
2725
+ kind: page
2726
+ value: ''
2727
+ - id: oll-v2-a9f5c91e3b09
2728
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Llama-2-7b-chat-hf/results_2025-02-13T18-27-04.338360.json
2729
+ fetch: conditional_http
2730
+ normaliser: text-default
2731
+ cited_regions:
2732
+ - id: rows
2733
+ locator:
2734
+ kind: page
2735
+ value: ''
2736
+ - id: oll-v2-ab4baf2ba301
2737
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/NousResearch/Hermes-2-Pro-Llama-3-8B/results_2025-02-13T18-27-04.338360.json
2738
+ fetch: conditional_http
2739
+ normaliser: text-default
2740
+ cited_regions:
2741
+ - id: rows
2742
+ locator:
2743
+ kind: page
2744
+ value: ''
2745
+ - id: oll-v2-ab8a90e29d5c
2746
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/stabilityai/stablelm-2-1_6b/results_2025-02-13T18-27-04.338360.json
2747
+ fetch: conditional_http
2748
+ normaliser: text-default
2749
+ cited_regions:
2750
+ - id: rows
2751
+ locator:
2752
+ kind: page
2753
+ value: ''
2754
+ - id: oll-v2-af12f1f21a63
2755
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Llama-3.1-8B-Instruct/results_2025-02-13T18-27-04.338360.json
2756
+ fetch: conditional_http
2757
+ normaliser: text-default
2758
+ cited_regions:
2759
+ - id: rows
2760
+ locator:
2761
+ kind: page
2762
+ value: ''
2763
+ - id: oll-v2-af20b21ee305
2764
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/tiiuae/falcon-7b-instruct/results_2025-02-13T18-27-04.338360.json
2765
+ fetch: conditional_http
2766
+ normaliser: text-default
2767
+ cited_regions:
2768
+ - id: rows
2769
+ locator:
2770
+ kind: page
2771
+ value: ''
2772
+ - id: oll-v2-b15cb033af45
2773
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/teknium/OpenHermes-13B/results_2025-02-13T18-27-04.338360.json
2774
+ fetch: conditional_http
2775
+ normaliser: text-default
2776
+ cited_regions:
2777
+ - id: rows
2778
+ locator:
2779
+ kind: page
2780
+ value: ''
2781
+ - id: oll-v2-b22408aab222
2782
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/Qwen/Qwen2-1.5B-Instruct/results_2025-02-13T18-27-04.338360.json
2783
+ fetch: conditional_http
2784
+ normaliser: text-default
2785
+ cited_regions:
2786
+ - id: rows
2787
+ locator:
2788
+ kind: page
2789
+ value: ''
2790
+ - id: oll-v2-b2a6a33491f5
2791
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/mistralai/Mistral-7B-v0.1/results_2025-02-13T18-27-04.338360.json
2792
+ fetch: conditional_http
2793
+ normaliser: text-default
2794
+ cited_regions:
2795
+ - id: rows
2796
+ locator:
2797
+ kind: page
2798
+ value: ''
2799
+ - id: oll-v2-b7bb2568bc11
2800
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/mistralai/Mistral-7B-v0.1/results_2024-10-24T00-00-00.000000.json
2801
+ fetch: conditional_http
2802
+ normaliser: text-default
2803
+ cited_regions:
2804
+ - id: rows
2805
+ locator:
2806
+ kind: page
2807
+ value: ''
2808
+ - id: oll-v2-baad7eadbc7a
2809
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Llama-2-13b-hf/results_2025-02-13T18-27-04.338360.json
2810
+ fetch: conditional_http
2811
+ normaliser: text-default
2812
+ cited_regions:
2813
+ - id: rows
2814
+ locator:
2815
+ kind: page
2816
+ value: ''
2817
+ - id: oll-v2-bc492862e9bf
2818
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/gemma-7b-it/results_2024-10-24T00-00-00.000000.json
2819
+ fetch: conditional_http
2820
+ normaliser: text-default
2821
+ cited_regions:
2822
+ - id: rows
2823
+ locator:
2824
+ kind: page
2825
+ value: ''
2826
+ - id: oll-v2-c106b23f2e93
2827
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/teknium/OpenHermes-2-Mistral-7B/results_2025-02-13T18-27-04.338360.json
2828
+ fetch: conditional_http
2829
+ normaliser: text-default
2830
+ cited_regions:
2831
+ - id: rows
2832
+ locator:
2833
+ kind: page
2834
+ value: ''
2835
+ - id: oll-v2-ca5160f3f7b5
2836
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Llama-2-70b-chat-hf/results_2025-02-13T18-27-04.338360.json
2837
+ fetch: conditional_http
2838
+ normaliser: text-default
2839
+ cited_regions:
2840
+ - id: rows
2841
+ locator:
2842
+ kind: page
2843
+ value: ''
2844
+ - id: oll-v2-cb8d93614572
2845
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/tiiuae/falcon-7b/results_2025-02-13T18-27-04.338360.json
2846
+ fetch: conditional_http
2847
+ normaliser: text-default
2848
+ cited_regions:
2849
+ - id: rows
2850
+ locator:
2851
+ kind: page
2852
+ value: ''
2853
+ - id: oll-v2-cc487415d228
2854
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Llama-3.2-3B-Instruct/results_2025-02-13T18-27-04.338360.json
2855
+ fetch: conditional_http
2856
+ normaliser: text-default
2857
+ cited_regions:
2858
+ - id: rows
2859
+ locator:
2860
+ kind: page
2861
+ value: ''
2862
+ - id: oll-v2-cdb3e982b1cc
2863
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/tiiuae/Falcon3-7B-Instruct/results_2025-02-13T18-27-04.338360.json
2864
+ fetch: conditional_http
2865
+ normaliser: text-default
2866
+ cited_regions:
2867
+ - id: rows
2868
+ locator:
2869
+ kind: page
2870
+ value: ''
2871
+ - id: oll-v2-cdb648166dd5
2872
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/gemma-7b-it/results_2025-02-13T18-27-04.338360.json
2873
+ fetch: conditional_http
2874
+ normaliser: text-default
2875
+ cited_regions:
2876
+ - id: rows
2877
+ locator:
2878
+ kind: page
2879
+ value: ''
2880
+ - id: oll-v2-d0eb128abed6
2881
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/mistralai/Ministral-8B-Instruct-2410/results_2025-02-13T18-27-04.338360.json
2882
+ fetch: conditional_http
2883
+ normaliser: text-default
2884
+ cited_regions:
2885
+ - id: rows
2886
+ locator:
2887
+ kind: page
2888
+ value: ''
2889
+ - id: oll-v2-d224d7ceab29
2890
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/Qwen/Qwen2.5-3B-Instruct/results_2025-02-13T18-27-04.338360.json
2891
+ fetch: conditional_http
2892
+ normaliser: text-default
2893
+ cited_regions:
2894
+ - id: rows
2895
+ locator:
2896
+ kind: page
2897
+ value: ''
2898
+ - id: oll-v2-d5247d695d91
2899
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Meta-Llama-3-70B/results_2025-02-13T18-27-04.338360.json
2900
+ fetch: conditional_http
2901
+ normaliser: text-default
2902
+ cited_regions:
2903
+ - id: rows
2904
+ locator:
2905
+ kind: page
2906
+ value: ''
2907
+ - id: oll-v2-d8f8f3f1e41f
2908
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/BAAI/Infinity-Instruct-3M-0625-Yi-1.5-9B/results_2025-02-13T18-27-04.338360.json
2909
+ fetch: conditional_http
2910
+ normaliser: text-default
2911
+ cited_regions:
2912
+ - id: rows
2913
+ locator:
2914
+ kind: page
2915
+ value: ''
2916
+ - id: oll-v2-d92e847cb221
2917
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/microsoft/Phi-4-mini-instruct/results_2025-02-28T12-41-07.003145.json
2918
+ fetch: conditional_http
2919
+ normaliser: text-default
2920
+ cited_regions:
2921
+ - id: rows
2922
+ locator:
2923
+ kind: page
2924
+ value: ''
2925
+ - id: oll-v2-db2ef33d2032
2926
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/gemma-2-2b-it/results_2024-07-29T16-25-50.870458.json
2927
+ fetch: conditional_http
2928
+ normaliser: text-default
2929
+ cited_regions:
2930
+ - id: rows
2931
+ locator:
2932
+ kind: page
2933
+ value: ''
2934
+ - id: oll-v2-e0eae55cc824
2935
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/Qwen/Qwen2-0.5B-Instruct/results_2025-02-13T18-27-04.338360.json
2936
+ fetch: conditional_http
2937
+ normaliser: text-default
2938
+ cited_regions:
2939
+ - id: rows
2940
+ locator:
2941
+ kind: page
2942
+ value: ''
2943
+ - id: oll-v2-e25990329031
2944
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/Qwen/Qwen2.5-0.5B/results_2025-02-13T18-27-04.338360.json
2945
+ fetch: conditional_http
2946
+ normaliser: text-default
2947
+ cited_regions:
2948
+ - id: rows
2949
+ locator:
2950
+ kind: page
2951
+ value: ''
2952
+ - id: oll-v2-e82235f7b81a
2953
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/allenai/OLMoE-1B-7B-0924/results_2025-02-13T18-27-04.338360.json
2954
+ fetch: conditional_http
2955
+ normaliser: text-default
2956
+ cited_regions:
2957
+ - id: rows
2958
+ locator:
2959
+ kind: page
2960
+ value: ''
2961
+ - id: oll-v2-e85b8ac91450
2962
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Llama-2-13b-chat-hf/results_2025-02-13T18-27-04.338360.json
2963
+ fetch: conditional_http
2964
+ normaliser: text-default
2965
+ cited_regions:
2966
+ - id: rows
2967
+ locator:
2968
+ kind: page
2969
+ value: ''
2970
+ - id: oll-v2-ec09a9f990c8
2971
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Meta-Llama-3-8B/results_2025-02-13T18-27-04.338360.json
2972
+ fetch: conditional_http
2973
+ normaliser: text-default
2974
+ cited_regions:
2975
+ - id: rows
2976
+ locator:
2977
+ kind: page
2978
+ value: ''
2979
+ - id: oll-v2-ef5fe1b9dd7f
2980
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/microsoft/Phi-3-mini-128k-instruct/results_2025-02-13T18-27-04.338360.json
2981
+ fetch: conditional_http
2982
+ normaliser: text-default
2983
+ cited_regions:
2984
+ - id: rows
2985
+ locator:
2986
+ kind: page
2987
+ value: ''
2988
+ - id: oll-v2-f03663972ad0
2989
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-1.5-6B-Chat/results_2025-02-13T18-27-04.338360.json
2990
+ fetch: conditional_http
2991
+ normaliser: text-default
2992
+ cited_regions:
2993
+ - id: rows
2994
+ locator:
2995
+ kind: page
2996
+ value: ''
2997
+ - id: oll-v2-f31d3312f266
2998
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/google/gemma-1.1-2b-it/results_2025-02-13T18-27-04.338360.json
2999
+ fetch: conditional_http
3000
+ normaliser: text-default
3001
+ cited_regions:
3002
+ - id: rows
3003
+ locator:
3004
+ kind: page
3005
+ value: ''
3006
+ - id: oll-v2-f6ed5ac64efd
3007
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/meta-llama/Llama-3.2-1B-Instruct/results_2025-02-13T18-27-04.338360.json
3008
+ fetch: conditional_http
3009
+ normaliser: text-default
3010
+ cited_regions:
3011
+ - id: rows
3012
+ locator:
3013
+ kind: page
3014
+ value: ''
3015
+ - id: oll-v2-f6f6d67db80c
3016
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-1.5-6B/results_2025-02-13T18-27-04.338360.json
3017
+ fetch: conditional_http
3018
+ normaliser: text-default
3019
+ cited_regions:
3020
+ - id: rows
3021
+ locator:
3022
+ kind: page
3023
+ value: ''
3024
+ - id: oll-v2-f837ef728691
3025
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-1.5-34B-Chat-16K/results_2025-02-13T18-27-04.338360.json
3026
+ fetch: conditional_http
3027
+ normaliser: text-default
3028
+ cited_regions:
3029
+ - id: rows
3030
+ locator:
3031
+ kind: page
3032
+ value: ''
3033
+ - id: oll-v2-f8c7af807038
3034
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-6B-200K/results_2025-02-13T18-27-04.338360.json
3035
+ fetch: conditional_http
3036
+ normaliser: text-default
3037
+ cited_regions:
3038
+ - id: rows
3039
+ locator:
3040
+ kind: page
3041
+ value: ''
3042
+ - id: oll-v2-fba6bc317570
3043
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/togethercomputer/Llama-2-7B-32K-Instruct/results_2025-02-13T18-27-04.338360.json
3044
+ fetch: conditional_http
3045
+ normaliser: text-default
3046
+ cited_regions:
3047
+ - id: rows
3048
+ locator:
3049
+ kind: page
3050
+ value: ''
3051
+ - id: oll-v2-fd80d18da80b
3052
+ url: https://huggingface.co/datasets/open-llm-leaderboard/results/resolve/aa81ecc38fdc5708254b833923368970efdf5ef5/01-ai/Yi-1.5-34B/results_2025-02-13T18-27-04.338360.json
3053
+ fetch: conditional_http
3054
+ normaliser: text-default
3055
+ cited_regions:
3056
+ - id: rows
3057
+ locator:
3058
+ kind: page
3059
+ value: ''