TobiasLogic commited on
Commit
bc69c2b
·
1 Parent(s): d939a50

Add cagliostro-v1 (157M) on bench 7-2026 (#13)

Browse files

- Add cagliostro-v1 (157M) on bench 7-2026 (99be9125e6b07e95894b3d2fcc942b6a26f4c80f)

Files changed (1) hide show
  1. models.json +414 -12
models.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "updated": "2026-08-03",
3
  "latest_generation": "7-2026",
4
  "benchmarks": [
5
  {
@@ -4956,6 +4956,402 @@
4956
  "notes": "Not yet evaluated on this tier."
4957
  }
4958
  }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4959
  }
4960
  ],
4961
  "t2i_benchmarks": [
@@ -4978,16 +5374,22 @@
4978
  ],
4979
  "t2i_models": [
4980
  {
4981
- "id": "bench-labs-pixelmodel-v6",
4982
- "name": "PixelModel v6",
4983
- "org": "Bench Labs",
4984
- "params_b": 0.1551,
4985
- "url": "https://huggingface.co/bench-labs/PixelModel-v6",
4986
- "resolution": "256x256",
4987
- "release_date": "2026-08-04",
4988
- "runs": {
4989
- "t2i-fid-coco": {"score": 23.62, "n": null},
4990
- "t2i-clip-coco": {"score": 0.3043, "n": null}
 
 
 
 
 
 
4991
  }
4992
  },
4993
  {
@@ -5144,4 +5546,4 @@
5144
  }
5145
  }
5146
  ]
5147
- }
 
1
  {
2
+ "updated": "2026-08-18",
3
  "latest_generation": "7-2026",
4
  "benchmarks": [
5
  {
 
4956
  "notes": "Not yet evaluated on this tier."
4957
  }
4958
  }
4959
+ },
4960
+ {
4961
+ "id": "bench-labs-cagliostro-v1",
4962
+ "name": "bench-labs/cagliostro-v1",
4963
+ "org": "bench-labs",
4964
+ "params_b": 0.157,
4965
+ "license": "mit",
4966
+ "architecture": "Qwen3",
4967
+ "url": "https://huggingface.co/bench-labs/cagliostro-v1",
4968
+ "model_revision": "5763fd50daf633d6203a3b157f85f86d19fa6b38",
4969
+ "script_sha256": "aaec13fe93213386afb3acdf3d927142fd35ac75db344241abc698d4571daac5",
4970
+ "runs": {
4971
+ "bench-effortless-7-2026": {
4972
+ "score": 0.02,
4973
+ "n": 300,
4974
+ "stderr": 0.0081,
4975
+ "metrics": {
4976
+ "generative": {
4977
+ "exact_match": 0.02,
4978
+ "hybrid_score": 0.2917
4979
+ },
4980
+ "loglikelihood": {
4981
+ "acc": 0.4533,
4982
+ "acc_norm": 0.49,
4983
+ "soft_score": 0.4533,
4984
+ "soft_score_norm": 0.49
4985
+ }
4986
+ },
4987
+ "categories": {
4988
+ "Commonsense-causality": {
4989
+ "n": 18,
4990
+ "score": 0.0,
4991
+ "exact_match": 0.0,
4992
+ "acc_norm": 0.6667
4993
+ },
4994
+ "Commonsense-reasoning": {
4995
+ "n": 18,
4996
+ "score": 0.0,
4997
+ "exact_match": 0.0,
4998
+ "acc_norm": 0.6667
4999
+ },
5000
+ "Commonsense-simulation": {
5001
+ "n": 18,
5002
+ "score": 0.0,
5003
+ "exact_match": 0.0,
5004
+ "acc_norm": 0.6111
5005
+ },
5006
+ "Knowledge-basic": {
5007
+ "n": 18,
5008
+ "score": 0.0,
5009
+ "exact_match": 0.0,
5010
+ "acc_norm": 0.3333
5011
+ },
5012
+ "Knowledge-definitions": {
5013
+ "n": 18,
5014
+ "score": 0.0,
5015
+ "exact_match": 0.0,
5016
+ "acc_norm": 0.7222
5017
+ },
5018
+ "Language-comprehension": {
5019
+ "n": 18,
5020
+ "score": 0.0,
5021
+ "exact_match": 0.0,
5022
+ "acc_norm": 0.7222
5023
+ },
5024
+ "Language-structure": {
5025
+ "n": 18,
5026
+ "score": 0.0,
5027
+ "exact_match": 0.0,
5028
+ "acc_norm": 0.2222
5029
+ },
5030
+ "Language-transformation": {
5031
+ "n": 18,
5032
+ "score": 0.0,
5033
+ "exact_match": 0.0,
5034
+ "acc_norm": 0.4444
5035
+ },
5036
+ "Logic-consistency": {
5037
+ "n": 18,
5038
+ "score": 0.1111,
5039
+ "exact_match": 0.1111,
5040
+ "acc_norm": 0.1667
5041
+ },
5042
+ "Logic-deduction": {
5043
+ "n": 18,
5044
+ "score": 0.1111,
5045
+ "exact_match": 0.1111,
5046
+ "acc_norm": 0.7778
5047
+ },
5048
+ "Logic-pattern": {
5049
+ "n": 18,
5050
+ "score": 0.1111,
5051
+ "exact_match": 0.1111,
5052
+ "acc_norm": 0.9444
5053
+ },
5054
+ "Math-arithmetic": {
5055
+ "n": 17,
5056
+ "score": 0.0,
5057
+ "exact_match": 0.0,
5058
+ "acc_norm": 0.4706
5059
+ },
5060
+ "Math-pattern": {
5061
+ "n": 17,
5062
+ "score": 0.0,
5063
+ "exact_match": 0.0,
5064
+ "acc_norm": 0.0588
5065
+ },
5066
+ "Math-reasoning": {
5067
+ "n": 17,
5068
+ "score": 0.0,
5069
+ "exact_match": 0.0,
5070
+ "acc_norm": 0.2353
5071
+ },
5072
+ "Pattern-generation": {
5073
+ "n": 17,
5074
+ "score": 0.0,
5075
+ "exact_match": 0.0,
5076
+ "acc_norm": 0.5882
5077
+ },
5078
+ "Pattern-matching": {
5079
+ "n": 17,
5080
+ "score": 0.0,
5081
+ "exact_match": 0.0,
5082
+ "acc_norm": 0.4706
5083
+ },
5084
+ "Pattern-recognition": {
5085
+ "n": 17,
5086
+ "score": 0.0,
5087
+ "exact_match": 0.0,
5088
+ "acc_norm": 0.1765
5089
+ }
5090
+ }
5091
+ },
5092
+ "bench-easy-7-2026": {
5093
+ "score": 0.3002,
5094
+ "n": 300,
5095
+ "stderr": 0.0214,
5096
+ "metrics": {
5097
+ "generative": {
5098
+ "exact_match": 0.0233,
5099
+ "hybrid_score": 0.3002
5100
+ },
5101
+ "loglikelihood": {
5102
+ "acc": 0.3767,
5103
+ "acc_norm": 0.4733,
5104
+ "soft_score": 0.3767,
5105
+ "soft_score_norm": 0.4733
5106
+ }
5107
+ },
5108
+ "categories": {
5109
+ "Commonsense-causality": {
5110
+ "n": 18,
5111
+ "score": 0.8076,
5112
+ "exact_match": 0.0556,
5113
+ "acc_norm": 0.6111
5114
+ },
5115
+ "Commonsense-reasoning": {
5116
+ "n": 18,
5117
+ "score": 0.7233,
5118
+ "exact_match": 0.0556,
5119
+ "acc_norm": 0.6667
5120
+ },
5121
+ "Commonsense-simulation": {
5122
+ "n": 18,
5123
+ "score": 0.7322,
5124
+ "exact_match": 0.0,
5125
+ "acc_norm": 0.5
5126
+ },
5127
+ "Knowledge-basic": {
5128
+ "n": 18,
5129
+ "score": 0.0,
5130
+ "exact_match": 0.0,
5131
+ "acc_norm": 0.4444
5132
+ },
5133
+ "Knowledge-definitions": {
5134
+ "n": 18,
5135
+ "score": 0.7631,
5136
+ "exact_match": 0.0,
5137
+ "acc_norm": 0.9444
5138
+ },
5139
+ "Language-comprehension": {
5140
+ "n": 18,
5141
+ "score": 0.7301,
5142
+ "exact_match": 0.0556,
5143
+ "acc_norm": 0.7222
5144
+ },
5145
+ "Language-structure": {
5146
+ "n": 18,
5147
+ "score": 0.2818,
5148
+ "exact_match": 0.0,
5149
+ "acc_norm": 0.2222
5150
+ },
5151
+ "Language-transformation": {
5152
+ "n": 18,
5153
+ "score": 0.7434,
5154
+ "exact_match": 0.0,
5155
+ "acc_norm": 0.5556
5156
+ },
5157
+ "Logic-consistency": {
5158
+ "n": 18,
5159
+ "score": 0.0,
5160
+ "exact_match": 0.0,
5161
+ "acc_norm": 0.0556
5162
+ },
5163
+ "Logic-deduction": {
5164
+ "n": 18,
5165
+ "score": 0.0556,
5166
+ "exact_match": 0.0556,
5167
+ "acc_norm": 0.7222
5168
+ },
5169
+ "Logic-pattern": {
5170
+ "n": 18,
5171
+ "score": 0.1667,
5172
+ "exact_match": 0.1667,
5173
+ "acc_norm": 0.6667
5174
+ },
5175
+ "Math-arithmetic": {
5176
+ "n": 17,
5177
+ "score": 0.0,
5178
+ "exact_match": 0.0,
5179
+ "acc_norm": 0.1176
5180
+ },
5181
+ "Math-pattern": {
5182
+ "n": 17,
5183
+ "score": 0.0,
5184
+ "exact_match": 0.0,
5185
+ "acc_norm": 0.2353
5186
+ },
5187
+ "Math-reasoning": {
5188
+ "n": 17,
5189
+ "score": 0.0,
5190
+ "exact_match": 0.0,
5191
+ "acc_norm": 0.2353
5192
+ },
5193
+ "Pattern-generation": {
5194
+ "n": 17,
5195
+ "score": 0.0,
5196
+ "exact_match": 0.0,
5197
+ "acc_norm": 0.5882
5198
+ },
5199
+ "Pattern-matching": {
5200
+ "n": 17,
5201
+ "score": 0.0,
5202
+ "exact_match": 0.0,
5203
+ "acc_norm": 0.4706
5204
+ },
5205
+ "Pattern-recognition": {
5206
+ "n": 17,
5207
+ "score": 0.0,
5208
+ "exact_match": 0.0,
5209
+ "acc_norm": 0.2353
5210
+ }
5211
+ }
5212
+ },
5213
+ "bench-mid-7-2026": {
5214
+ "score": 0.3867,
5215
+ "n": 300,
5216
+ "stderr": 0.0282,
5217
+ "metrics": {
5218
+ "generative": {
5219
+ "exact_match": 0.01,
5220
+ "hybrid_score": 0.2803
5221
+ },
5222
+ "loglikelihood": {
5223
+ "acc": 0.3167,
5224
+ "acc_norm": 0.3867,
5225
+ "soft_score": 0.3167,
5226
+ "soft_score_norm": 0.3867
5227
+ }
5228
+ },
5229
+ "categories": {
5230
+ "Commonsense-causality": {
5231
+ "n": 18,
5232
+ "score": 0.5556,
5233
+ "exact_match": 0.0,
5234
+ "acc_norm": 0.5556
5235
+ },
5236
+ "Commonsense-reasoning": {
5237
+ "n": 18,
5238
+ "score": 0.4444,
5239
+ "exact_match": 0.0,
5240
+ "acc_norm": 0.4444
5241
+ },
5242
+ "Commonsense-simulation": {
5243
+ "n": 18,
5244
+ "score": 0.3333,
5245
+ "exact_match": 0.0,
5246
+ "acc_norm": 0.3333
5247
+ },
5248
+ "Knowledge-basic": {
5249
+ "n": 18,
5250
+ "score": 0.5556,
5251
+ "exact_match": 0.1111,
5252
+ "acc_norm": 0.5556
5253
+ },
5254
+ "Knowledge-definitions": {
5255
+ "n": 18,
5256
+ "score": 0.6667,
5257
+ "exact_match": 0.0,
5258
+ "acc_norm": 0.6667
5259
+ },
5260
+ "Language-comprehension": {
5261
+ "n": 18,
5262
+ "score": 0.3889,
5263
+ "exact_match": 0.0,
5264
+ "acc_norm": 0.3889
5265
+ },
5266
+ "Language-structure": {
5267
+ "n": 18,
5268
+ "score": 0.5,
5269
+ "exact_match": 0.0,
5270
+ "acc_norm": 0.5
5271
+ },
5272
+ "Language-transformation": {
5273
+ "n": 18,
5274
+ "score": 0.6667,
5275
+ "exact_match": 0.0,
5276
+ "acc_norm": 0.6667
5277
+ },
5278
+ "Logic-consistency": {
5279
+ "n": 18,
5280
+ "score": 0.0556,
5281
+ "exact_match": 0.0,
5282
+ "acc_norm": 0.0556
5283
+ },
5284
+ "Logic-deduction": {
5285
+ "n": 18,
5286
+ "score": 0.5556,
5287
+ "exact_match": 0.0,
5288
+ "acc_norm": 0.5556
5289
+ },
5290
+ "Logic-pattern": {
5291
+ "n": 18,
5292
+ "score": 0.3889,
5293
+ "exact_match": 0.0,
5294
+ "acc_norm": 0.3889
5295
+ },
5296
+ "Math-arithmetic": {
5297
+ "n": 17,
5298
+ "score": 0.1765,
5299
+ "exact_match": 0.0,
5300
+ "acc_norm": 0.1765
5301
+ },
5302
+ "Math-pattern": {
5303
+ "n": 17,
5304
+ "score": 0.2353,
5305
+ "exact_match": 0.0,
5306
+ "acc_norm": 0.2353
5307
+ },
5308
+ "Math-reasoning": {
5309
+ "n": 17,
5310
+ "score": 0.1176,
5311
+ "exact_match": 0.0,
5312
+ "acc_norm": 0.1176
5313
+ },
5314
+ "Pattern-generation": {
5315
+ "n": 17,
5316
+ "score": 0.4118,
5317
+ "exact_match": 0.0588,
5318
+ "acc_norm": 0.4118
5319
+ },
5320
+ "Pattern-matching": {
5321
+ "n": 17,
5322
+ "score": 0.4706,
5323
+ "exact_match": 0.0,
5324
+ "acc_norm": 0.4706
5325
+ },
5326
+ "Pattern-recognition": {
5327
+ "n": 17,
5328
+ "score": 0.0,
5329
+ "exact_match": 0.0,
5330
+ "acc_norm": 0.0
5331
+ }
5332
+ }
5333
+ },
5334
+ "bench-effortless-6-2026": {
5335
+ "score": null,
5336
+ "n": null,
5337
+ "notes": "Not yet evaluated on this tier."
5338
+ },
5339
+ "bench-easy-6-2026": {
5340
+ "score": null,
5341
+ "n": null,
5342
+ "notes": "Not yet evaluated on this tier."
5343
+ },
5344
+ "bench-mid-6-2026": {
5345
+ "score": null,
5346
+ "n": null,
5347
+ "notes": "Not yet evaluated on this tier."
5348
+ },
5349
+ "bench-AGI": {
5350
+ "score": null,
5351
+ "n": null,
5352
+ "notes": "Not yet evaluated on this tier."
5353
+ }
5354
+ }
5355
  }
5356
  ],
5357
  "t2i_benchmarks": [
 
5374
  ],
5375
  "t2i_models": [
5376
  {
5377
+ "id": "bench-labs-pixelmodel-v6",
5378
+ "name": "PixelModel v6",
5379
+ "org": "Bench Labs",
5380
+ "params_b": 0.1551,
5381
+ "url": "https://huggingface.co/bench-labs/PixelModel-v6",
5382
+ "resolution": "256x256",
5383
+ "release_date": "2026-08-04",
5384
+ "runs": {
5385
+ "t2i-fid-coco": {
5386
+ "score": 23.62,
5387
+ "n": null
5388
+ },
5389
+ "t2i-clip-coco": {
5390
+ "score": 0.3043,
5391
+ "n": null
5392
+ }
5393
  }
5394
  },
5395
  {
 
5546
  }
5547
  }
5548
  ]
5549
+ }