Browse the data

Every graded trial in the benchmark. Scan the heatmap, read the task catalog, or filter the trial table. Every cell opens the agent's full trajectory.

Task
Model
Wallet
882 trials
AI-text detectionClaude Opus 5.5$1098.3$7.01$76.688h 53m199
AI-text detectionClaude Opus 5.5$5098.9$40.72$60.617h207
AI-text detectionClaude Opus 5.5$20099.2$80.08$69.167h 40m251
AI-text detectionClaude Sonnet 5.5$1096.1$8.13$28.314h 50m381
AI-text detectionClaude Sonnet 5.5$5096.1$46.29$21.986h 30m443
AI-text detectionClaude Sonnet 5.5$20094.9$81.50$22.314h 10m382
AI-text detectionClaude Fable 5.1$1071.9$9.12$24.903h 25m182
AI-text detectionClaude Fable 5.1$5083.6$25.94$64.043h 55m174
AI-text detectionClaude Fable 5.1$20083.2$123.89$98.165h 17m111
AI-text detectionClaude Haiku 5.5$1086.8$4.27$5.312h 26m267
AI-text detectionClaude Haiku 5.5$5093.8$26.76$7.035h 28m321
AI-text detectionClaude Haiku 5.5$20074.1$28.23$9.465h 50m388
AI-text detectionGPT-6 Astra$1090.7$6.98$25.581h 11m133
AI-text detectionGPT-6 Astra$5091.9$20.94$54.851h 48m284
AI-text detectionGPT-6 Astra$20094.2$41.88$42.511h 59m210
AI-text detectionGPT-6.1 Sol$1090.8$8.82$4.001h 2m134
AI-text detectionGPT-6.1 Sol$5087.2$21.35$5.232h 30m182
AI-text detectionGPT-6.1 Sol$20089.5$38.14$4.942h 7m158
AI-text detectionGPT-6 Luna$1083.8$6.98$0.4950m229
AI-text detectionGPT-6 Luna$5084.0$5.76$0.4249m246
AI-text detectionGPT-6 Luna$20084.6$13.96$0.4547m262
AI-text detectionGemini 3.8 Flash$109.4$0.45$8.1058m651
AI-text detectionGemini 3.8 Flash$5064.4$0.90$8.7340m648
AI-text detectionGemini 3.8 Flash$2000.0$3.49$4.6240m337
AI-text detectionGrok 4.7$1044.1$1.03$26.324h 1m100
AI-text detectionGrok 4.7$5083.0$2.36$25.702h 8m126
AI-text detectionGrok 4.7$20084.5$30.62$25.913h 58m177
AI-text detectionMuse Spark 1.3$1063.2$5.67$13.0210h 14m331
AI-text detectionMuse Spark 1.3$5043.5$8.18$10.735h 29m228
AI-text detectionMuse Spark 1.3$20056.3$5.66$11.806h 39m240
AI-text detectionMuse Wonder$1073.0$3.60$25.296h 9m284
AI-text detectionMuse Wonder$5048.8$4.50$25.248h 13m282
AI-text detectionMuse Wonder$20069.2$36.46$12.346h 24m213
AI-text detectionKimi K3$1066.6$8.55$33.757h 13m370
AI-text detectionKimi K3$5047.4$38.39$26.339h 26m357
AI-text detectionKimi K3$20068.9$59.98$21.118h 41m321
AI-text detectionQwen3.8 Max$1076.5$8.51$20.3610h 22m308
AI-text detectionQwen3.8 Max$5063.8$34.26$16.296h 34m441
AI-text detectionQwen3.8 Max$20054.1$15.42$8.344h 59m211
AI-text detectionGLM 5.3$1091.0$5.52$19.923h 32m290
AI-text detectionGLM 5.3$5055.2$21.85$10.339h 10m523
AI-text detectionGLM 5.3$20092.3$47.09$7.788h 6m422
AR to diffusion conversionClaude Opus 5.5$100.0$9.84$59.485h 13m333
AR to diffusion conversionClaude Opus 5.5$5080.9$38.05$124.009h 29m337
AR to diffusion conversionClaude Opus 5.5$20069.5$192.54$57.316h 25m328
AR to diffusion conversionClaude Sonnet 5.5$1030.2$10.00$39.896h 44m593
AR to diffusion conversionClaude Sonnet 5.5$500.0$49.09$61.219h 18m1001
AR to diffusion conversionClaude Sonnet 5.5$20047.6$169.27$50.2110h 45m802
AR to diffusion conversionClaude Fable 5.1$100.0$9.90$73.426h 25m292
AR to diffusion conversionClaude Fable 5.1$5076.7$26.88$54.544h 22m141
AR to diffusion conversionClaude Fable 5.1$20027.9$167.52$122.445h 28m215
AR to diffusion conversionClaude Haiku 5.5$100.3$8.44$7.973h 45m318
AR to diffusion conversionClaude Haiku 5.5$5012.3$28.89$15.986h344
AR to diffusion conversionClaude Haiku 5.5$20039.2$153.56$10.694h 37m360
AR to diffusion conversionGPT-6 Astra$104.8$9.89$67.432h 48m311
AR to diffusion conversionGPT-6 Astra$502.1$49.98$128.184h 46m573
AR to diffusion conversionGPT-6 Astra$2000.0$199.59$205.659h 14m845
AR to diffusion conversionGPT-6.1 Sol$101.7$9.83$7.663h 25m237
AR to diffusion conversionGPT-6.1 Sol$5055.3$48.86$16.329h 50m441
AR to diffusion conversionGPT-6.1 Sol$20045.9$197.77$17.249h 13m459
AR to diffusion conversionGPT-6 Luna$100.0$3.49$0.551h 4m302
AR to diffusion conversionGPT-6 Luna$502.1$38.39$3.2510h 47m1774
AR to diffusion conversionGPT-6 Luna$2000.5$7.57$0.762h 10m359
AR to diffusion conversionGemini 3.8 Flash$100.0$0.00$28.9612h1724
AR to diffusion conversionGemini 3.8 Flash$500.0$0.00$26.862h 26m1478
AR to diffusion conversionGemini 3.8 Flash$2000.0$0.00$6.7812h410
AR to diffusion conversionGrok 4.7$100.0$9.74$67.106h 9m163
AR to diffusion conversionGrok 4.7$500.0$34.90$60.375h 24m57
AR to diffusion conversionGrok 4.7$2000.0$38.39$63.184h 14m283
AR to diffusion conversionMuse Spark 1.3$100.2$8.93$29.5310h 52m600
AR to diffusion conversionMuse Spark 1.3$500.0$49.92$28.6311h 55m606
AR to diffusion conversionMuse Spark 1.3$2000.0$34.52$13.549h 5m324
AR to diffusion conversionMuse Wonder$100.8$9.38$33.757h 1m393
AR to diffusion conversionMuse Wonder$501.0$17.82$51.689h 59m547
AR to diffusion conversionMuse Wonder$2002.8$41.88$35.049h 23m369
AR to diffusion conversionKimi K3$100.0$9.83$34.984h 45m311
AR to diffusion conversionKimi K3$500.0$34.56$54.539h 2m461
AR to diffusion conversionKimi K3$2009.3$199.99$41.407h 56m406
AR to diffusion conversionQwen3.8 Max$100.0$9.95$1.286h 16m342
AR to diffusion conversionQwen3.8 Max$500.1$49.50$11.365h 55m235
AR to diffusion conversionQwen3.8 Max$2000.0$76.66$4.4312h385
AR to diffusion conversionGLM 5.3$100.0$8.63$5.342h 49m205
AR to diffusion conversionGLM 5.3$500.0$45.00$20.3810h 6m795
AR to diffusion conversionGLM 5.3$2000.0$65.69$16.2712h 1m758
Data-efficient pretrainingClaude Opus 5.5$1065.1$9.60$26.533h 17m198
Data-efficient pretrainingClaude Opus 5.5$5083.1$41.88$42.776h 26m194
Data-efficient pretrainingClaude Opus 5.5$20099.8$129.13$25.495h 2m233
Data-efficient pretrainingClaude Sonnet 5.5$1047.8$7.53$28.876h 59m345
Data-efficient pretrainingClaude Sonnet 5.5$5071.1$34.90$29.089h 45m351
Data-efficient pretrainingClaude Sonnet 5.5$20080.5$108.19$25.9410h 31m332
Data-efficient pretrainingClaude Fable 5.1$1026.9$5.59$48.863h 25m122
Data-efficient pretrainingClaude Fable 5.1$5040.9$24.43$102.305h 53m154
Data-efficient pretrainingClaude Fable 5.1$20080.6$34.90$91.525h 11m129
Data-efficient pretrainingClaude Haiku 5.5$1049.5$8.73$4.722h 30m152
Data-efficient pretrainingClaude Haiku 5.5$5067.2$26.18$12.766h 26m192
Data-efficient pretrainingClaude Haiku 5.5$20049.2$55.17$10.706h 13m254
Data-efficient pretrainingGPT-6 Astra$1059.5$8.73$42.482h 11m281
Data-efficient pretrainingGPT-6 Astra$5077.8$20.94$51.042h 17m235
Data-efficient pretrainingGPT-6 Astra$20074.5$46.54$34.401h 59m201
Data-efficient pretrainingGPT-6.1 Sol$1040.9$9.89$4.582h 33m134
Data-efficient pretrainingGPT-6.1 Sol$5077.5$18.04$4.632h 34m150
Data-efficient pretrainingGPT-6.1 Sol$20066.1$62.82$5.242h 49m134
Data-efficient pretrainingGPT-6 Luna$100.0$0.00$0.0819m56
Data-efficient pretrainingGPT-6 Luna$500.0$0.00$0.0920m58
Data-efficient pretrainingGPT-6 Luna$2000.0$0.00$0.0717m49
Data-efficient pretrainingGemini 3.8 Flash$100.0$0.00$6.2922m428
Data-efficient pretrainingGemini 3.8 Flash$500.0$0.00$5.3937m451
Data-efficient pretrainingGemini 3.8 Flash$2000.0$0.00$4.7358m291
Data-efficient pretrainingGrok 4.7$100.0$7.29$44.944h 1m273
Data-efficient pretrainingGrok 4.7$500.0$5.40$39.738h 46m230
Data-efficient pretrainingGrok 4.7$20016.3$27.92$32.055h 40m117
Data-efficient pretrainingMuse Spark 1.3$100.0$8.82$8.858h 7m214
Data-efficient pretrainingMuse Spark 1.3$500.0$19.96$6.783h 50m196
Data-efficient pretrainingMuse Spark 1.3$2000.0$37.66$16.754h 52m318
Data-efficient pretrainingMuse Wonder$1033.8$9.90$11.586h 2m187
Data-efficient pretrainingMuse Wonder$5018.9$13.96$6.673h 41m130
Data-efficient pretrainingMuse Wonder$2005.5$31.41$9.704h 22m165
Data-efficient pretrainingKimi K3$100.0$9.89$9.783h 29m158
Data-efficient pretrainingKimi K3$5013.7$38.39$36.3010h 17m420
Data-efficient pretrainingKimi K3$20036.3$63.16$53.139h 29m383
Data-efficient pretrainingQwen3.8 Max$1034.0$8.63$8.524h 17m199
Data-efficient pretrainingQwen3.8 Max$500.0$38.39$13.056h 43m277
Data-efficient pretrainingQwen3.8 Max$20049.5$40.47$13.787h 37m196
Data-efficient pretrainingGLM 5.3$1041.0$9.34$21.024h 50m259
Data-efficient pretrainingGLM 5.3$5037.8$16.87$17.444h 50m242
Data-efficient pretrainingGLM 5.3$20028.1$41.88$25.523h 52m374
Figure to TikZClaude Opus 5.5$1056.4$8.15$17.602h 31m188
Figure to TikZClaude Opus 5.5$5057.0$40.52$22.349h 12m327
Figure to TikZClaude Opus 5.5$20065.1$136.11$38.155h 5m239
Figure to TikZClaude Sonnet 5.5$1054.7$8.76$21.513h 41m455
Figure to TikZClaude Sonnet 5.5$5057.7$31.38$24.066h 58m549
Figure to TikZClaude Sonnet 5.5$20058.7$196.61$36.629h 12m482
Figure to TikZClaude Fable 5.1$1054.5$8.67$80.384h 46m119
Figure to TikZClaude Fable 5.1$5054.0$29.15$107.176h 32m145
Figure to TikZClaude Fable 5.1$20056.5$95.98$161.497h 53m183
Figure to TikZClaude Haiku 5.5$1042.4$7.81$7.013h 26m335
Figure to TikZClaude Haiku 5.5$5053.3$27.92$7.896h 34m382
Figure to TikZClaude Haiku 5.5$20052.2$41.88$10.965h 41m324
Figure to TikZGPT-6 Astra$1052.9$10.00$182.358h 2m963
Figure to TikZGPT-6 Astra$5057.0$49.74$248.8611h1265
Figure to TikZGPT-6 Astra$20059.1$160.54$109.274h 23m596
Figure to TikZGPT-6.1 Sol$1050.5$9.99$6.723h 43m228
Figure to TikZGPT-6.1 Sol$5051.0$39.56$9.598h 35m347
Figure to TikZGPT-6.1 Sol$20060.4$195.44$10.796h 19m317
Figure to TikZGPT-6 Luna$1041.4$5.76$0.861h 29m478
Figure to TikZGPT-6 Luna$5045.7$34.90$0.944h 33m678
Figure to TikZGPT-6 Luna$20032.9$34.52$1.346h 34m1018
Figure to TikZGemini 3.8 Flash$1030.6$2.48$9.021h 50m601
Figure to TikZGemini 3.8 Flash$5027.8$1.49$38.282h 27m2681
Figure to TikZGemini 3.8 Flash$20034.9$6.98$8.0559m704
Figure to TikZGrok 4.7$1036.0$2.70$17.691h 57m114
Figure to TikZGrok 4.7$5035.5$11.88$24.447h 5m225
Figure to TikZGrok 4.7$2007.8$18.73$21.312h 58m31
Figure to TikZMuse Spark 1.3$1049.3$9.27$7.478h 10m220
Figure to TikZMuse Spark 1.3$5043.6$28.77$12.319h 2m272
Figure to TikZMuse Spark 1.3$20047.8$40.15$14.829h 11m314
Figure to TikZMuse Wonder$1041.4$8.91$10.004h 40m175
Figure to TikZMuse Wonder$5044.4$17.82$6.976h 58m149
Figure to TikZMuse Wonder$20043.0$31.65$15.278h 14m235
Figure to TikZKimi K3$1048.4$9.90$36.588h 21m407
Figure to TikZKimi K3$5048.3$31.41$19.147h 56m257
Figure to TikZKimi K3$20041.4$62.82$50.679h 41m419
Figure to TikZQwen3.8 Max$1044.4$7.80$11.915h 58m234
Figure to TikZQwen3.8 Max$5046.8$48.86$6.743h 56m158
Figure to TikZQwen3.8 Max$20056.3$115.06$16.779h404
Figure to TikZGLM 5.3$1039.5$9.92$5.633h 41m271
Figure to TikZGLM 5.3$5040.1$43.53$37.705h 31m562
Figure to TikZGLM 5.3$20049.0$48.91$29.808h 29m456
Inverse dynamics modelClaude Opus 5.5$1072.6$5.63$88.287h 29m330
Inverse dynamics modelClaude Opus 5.5$5066.9$25.30$62.887h 9m407
Inverse dynamics modelClaude Opus 5.5$20078.5$195.44$62.566h 55m265
Inverse dynamics modelClaude Sonnet 5.5$1073.3$7.86$54.788h 5m1051
Inverse dynamics modelClaude Sonnet 5.5$5069.0$10.07$120.899h 7m1783
Inverse dynamics modelClaude Sonnet 5.5$20079.1$180.94$247.247h 28m3484
Inverse dynamics modelClaude Fable 5.1$1056.8$2.70$97.904h 28m174
Inverse dynamics modelClaude Fable 5.1$5064.4$3.15$51.923h 44m178
Inverse dynamics modelClaude Fable 5.1$20063.2$34.90$22.561h 38m115
Inverse dynamics modelClaude Haiku 5.5$1032.2$7.86$4.142h 31m219
Inverse dynamics modelClaude Haiku 5.5$5043.2$16.58$11.184h 45m247
Inverse dynamics modelClaude Haiku 5.5$20037.4$13.96$6.943h 4m283
Inverse dynamics modelGPT-6 Astra$1044.9$4.60$29.0056m158
Inverse dynamics modelGPT-6 Astra$5055.9$13.96$42.951h 9m205
Inverse dynamics modelGPT-6 Astra$20067.2$20.14$34.221h 19m178
Inverse dynamics modelGPT-6.1 Sol$1045.8$2.97$4.071h 16m115
Inverse dynamics modelGPT-6.1 Sol$5053.7$17.45$4.841h 32m191
Inverse dynamics modelGPT-6.1 Sol$20039.9$13.96$5.161h 49m182
Inverse dynamics modelGPT-6 Luna$1036.5$0.00$0.391h 7m208
Inverse dynamics modelGPT-6 Luna$5030.2$6.98$0.3552m185
Inverse dynamics modelGPT-6 Luna$20016.3$27.92$0.872h 6m533
Inverse dynamics modelGemini 3.8 Flash$1034.8$0.01$6.5937m443
Inverse dynamics modelGemini 3.8 Flash$5031.4$5.20$14.731h 29m976
Inverse dynamics modelGemini 3.8 Flash$20016.1$3.72$23.902h 44m1542
Inverse dynamics modelGrok 4.7$1023.5$2.25$26.152h 14m189
Inverse dynamics modelGrok 4.7$5019.7$1.36$24.161h 31m195
Inverse dynamics modelGrok 4.7$20025.1$13.96$25.132h 24m116
Inverse dynamics modelMuse Spark 1.3$1019.3$2.70$34.756h 30m767
Inverse dynamics modelMuse Spark 1.3$5047.8$43.34$22.469h 34m529
Inverse dynamics modelMuse Spark 1.3$20046.0$35.18$20.9511h 27m357
Inverse dynamics modelMuse Wonder$1034.5$1.13$29.058h 24m359
Inverse dynamics modelMuse Wonder$5048.1$33.82$31.0210h 59m377
Inverse dynamics modelMuse Wonder$20029.5$11.88$10.804h 46m176
Inverse dynamics modelKimi K3$1034.7$2.88$67.2710h 16m525
Inverse dynamics modelKimi K3$5035.6$32.42$126.4910h 15m878
Inverse dynamics modelKimi K3$20031.6$39.92$75.9411h 2m602
Inverse dynamics modelQwen3.8 Max$1036.0$2.70$8.903h 40m217
Inverse dynamics modelQwen3.8 Max$5067.5$31.21$17.2610h 29m312
Inverse dynamics modelQwen3.8 Max$20057.3$172.18$12.305h 37m208
Inverse dynamics modelGLM 5.3$1034.4$5.40$42.187h 18m609
Inverse dynamics modelGLM 5.3$5035.0$30.42$17.939h 46m847
Inverse dynamics modelGLM 5.3$20034.1$15.51$59.787h 29m895
Lean proof validityClaude Opus 5.5$1037.5$8.87$13.832h 52m192
Lean proof validityClaude Opus 5.5$5045.3$35.49$31.226h 38m415
Lean proof validityClaude Opus 5.5$20057.5$168.53$49.476h 2m282
Lean proof validityClaude Sonnet 5.5$1041.8$8.41$30.639h 29m660
Lean proof validityClaude Sonnet 5.5$5031.9$38.85$30.287h 28m522
Lean proof validityClaude Sonnet 5.5$20057.9$167.54$30.626h 19m544
Lean proof validityClaude Fable 5.1$1028.6$8.29$58.834h 4m82
Lean proof validityClaude Fable 5.1$5040.7$31.50$96.255h 43m136
Lean proof validityClaude Fable 5.1$20043.2$62.82$55.785h 33m199
Lean proof validityClaude Haiku 5.5$1026.6$8.49$5.322h 59m299
Lean proof validityClaude Haiku 5.5$5026.6$29.64$6.755h 22m350
Lean proof validityClaude Haiku 5.5$20041.5$36.26$12.807h 28m393
Lean proof validityGPT-6 Astra$1037.5$9.15$138.495h 38m620
Lean proof validityGPT-6 Astra$5029.8$48.34$147.495h 41m696
Lean proof validityGPT-6 Astra$20035.8$169.24$146.106h 31m698
Lean proof validityGPT-6.1 Sol$1036.3$9.89$7.003h 1m210
Lean proof validityGPT-6.1 Sol$5027.7$48.27$13.498h 22m355
Lean proof validityGPT-6.1 Sol$20033.1$72.91$14.256h 15m342
Lean proof validityGPT-6 Luna$101.4$6.24$0.4549m250
Lean proof validityGPT-6 Luna$5015.7$8.63$0.881h 22m500
Lean proof validityGPT-6 Luna$2005.0$6.98$0.531h 2m292
Lean proof validityGemini 3.8 Flash$100.0$0.68$6.6544m450
Lean proof validityGemini 3.8 Flash$500.0$8.43$19.554h 17m1206
Lean proof validityGemini 3.8 Flash$2002.5$2.97$8.201h 8m579
Lean proof validityGrok 4.7$106.0$1.35$23.173h 4m49
Lean proof validityGrok 4.7$500.0$2.25$18.171h 43m226
Lean proof validityGrok 4.7$20012.1$8.60$21.262h 41m118
Lean proof validityMuse Spark 1.3$104.3$2.91$12.995h 17m308
Lean proof validityMuse Spark 1.3$5020.7$16.38$15.769h 14m356
Lean proof validityMuse Spark 1.3$2000.0$36.48$25.6912h529
Lean proof validityMuse Wonder$100.0$2.00$3.812h 29m93
Lean proof validityMuse Wonder$507.0$3.60$10.445h 22m194
Lean proof validityMuse Wonder$2000.1$29.85$12.988h 34m209
Lean proof validityKimi K3$1017.6$9.30$52.708h 53m555
Lean proof validityKimi K3$5017.2$42.77$34.9710h 26m472
Lean proof validityKimi K3$20020.6$44.08$49.0510h 14m520
Lean proof validityQwen3.8 Max$1018.0$9.66$13.237h 41m354
Lean proof validityQwen3.8 Max$500.0$43.28$16.277h 21m357
Lean proof validityQwen3.8 Max$2000.0$82.55$19.019h362
Lean proof validityGLM 5.3$100.0$9.30$31.305h 49m426
Lean proof validityGLM 5.3$500.0$22.28$39.827h 45m601
Lean proof validityGLM 5.3$2003.0$35.35$25.719h 35m387
LLM post-trainingClaude Opus 5.5$1057.6$7.86$33.223h 31m173
LLM post-trainingClaude Opus 5.5$5043.3$44.21$18.504h 7m203
LLM post-trainingClaude Opus 5.5$20067.4$173.34$53.776h 37m206
LLM post-trainingClaude Sonnet 5.5$1049.2$9.92$23.194h 27m321
LLM post-trainingClaude Sonnet 5.5$5049.3$46.00$39.879h 45m485
LLM post-trainingClaude Sonnet 5.5$20045.2$184.01$40.868h 19m885
LLM post-trainingClaude Fable 5.1$1026.0$6.98$38.902h 58m166
LLM post-trainingClaude Fable 5.1$5046.2$48.86$47.793h 30m146
LLM post-trainingClaude Fable 5.1$2000.0$181.48$86.575h 13m191
LLM post-trainingClaude Haiku 5.5$1040.9$9.02$5.673h 11m206
LLM post-trainingClaude Haiku 5.5$5017.4$37.82$18.708h 25m352
LLM post-trainingClaude Haiku 5.5$20061.3$99.58$11.636h 54m426
LLM post-trainingGPT-6 Astra$1051.6$9.31$51.952h 44m250
LLM post-trainingGPT-6 Astra$5048.3$49.61$90.927h 8m575
LLM post-trainingGPT-6 Astra$20067.2$188.46$142.146h 42m713
LLM post-trainingGPT-6.1 Sol$1011.5$9.70$5.543h 1m182
LLM post-trainingGPT-6.1 Sol$5065.7$49.72$6.839h 39m238
LLM post-trainingGPT-6.1 Sol$20036.6$177.28$10.525h 27m361
LLM post-trainingGPT-6 Luna$100.0$9.91$0.772h 10m449
LLM post-trainingGPT-6 Luna$500.0$43.18$2.649h 17m1549
LLM post-trainingGPT-6 Luna$2000.0$41.88$1.918h 49m1286
LLM post-trainingGemini 3.8 Flash$100.0$0.68$8.591h 29m619
LLM post-trainingGemini 3.8 Flash$500.0$10.47$49.164h 46m3206
LLM post-trainingGemini 3.8 Flash$2000.0$12.49$13.193h 49m757
LLM post-trainingGrok 4.7$100.0$9.59$21.773h 23m136
LLM post-trainingGrok 4.7$5016.1$7.42$18.887h 23m193
LLM post-trainingGrok 4.7$2000.0$34.53$23.6512h208
LLM post-trainingMuse Spark 1.3$1035.3$6.62$14.1811h 1m281
LLM post-trainingMuse Spark 1.3$500.0$35.64$12.3810h 25m315
LLM post-trainingMuse Spark 1.3$2000.0$80.55$26.4912h491
LLM post-trainingMuse Wonder$100.0$8.42$15.695h 29m224
LLM post-trainingMuse Wonder$5034.8$34.90$26.299h 52m330
LLM post-trainingMuse Wonder$20048.8$153.56$18.839h 32m275
LLM post-trainingKimi K3$1013.3$9.83$18.565h 55m186
LLM post-trainingKimi K3$5026.1$41.88$24.5010h 19m379
LLM post-trainingKimi K3$20012.9$197.37$47.5711h 26m491
LLM post-trainingQwen3.8 Max$100.0$9.90$1.398h 3m283
LLM post-trainingQwen3.8 Max$5038.1$49.85$24.9110h 23m287
LLM post-trainingQwen3.8 Max$2000.0$125.64$23.269h 37m591
LLM post-trainingGLM 5.3$1024.9$8.73$19.732h 43m213
LLM post-trainingGLM 5.3$5041.2$42.67$7.5610h 52m318
LLM post-trainingGLM 5.3$20034.3$37.65$3.857h 5m337
Math proof simplificationClaude Opus 5.5$1033.9$7.64$37.254h 19m275
Math proof simplificationClaude Opus 5.5$5029.4$23.50$64.325h 22m352
Math proof simplificationClaude Opus 5.5$20040.5$29.29$47.675h 16m281
Math proof simplificationClaude Sonnet 5.5$1031.6$6.52$32.015h 46m602
Math proof simplificationClaude Sonnet 5.5$5037.5$38.50$46.188h 31m987
Math proof simplificationClaude Sonnet 5.5$20034.9$37.97$31.157h 59m532
Math proof simplificationClaude Fable 5.1$1021.4$2.67$73.713h 39m188
Math proof simplificationClaude Fable 5.1$5029.8$9.11$38.172h 47m279
Math proof simplificationClaude Fable 5.1$20025.5$13.96$54.723h 14m192
Math proof simplificationClaude Haiku 5.5$1020.1$7.47$6.894h 11m323
Math proof simplificationClaude Haiku 5.5$5018.0$17.45$7.824h 56m295
Math proof simplificationClaude Haiku 5.5$20027.4$51.98$9.965h 31m406
Math proof simplificationGPT-6 Astra$1021.5$3.49$29.3158m156
Math proof simplificationGPT-6 Astra$5028.0$10.47$39.751h 17m195
Math proof simplificationGPT-6 Astra$20024.3$13.96$37.351h 40m191
Math proof simplificationGPT-6.1 Sol$1015.6$3.49$2.7953m123
Math proof simplificationGPT-6.1 Sol$5014.8$8.63$3.911h 22m122
Math proof simplificationGPT-6.1 Sol$2008.5$13.96$4.511h 31m141
Math proof simplificationGPT-6 Luna$102.8$0.00$0.4145m206
Math proof simplificationGPT-6 Luna$500.1$10.47$0.491h 4m259
Math proof simplificationGPT-6 Luna$2000.0$0.00$0.1823m90
Math proof simplificationGemini 3.8 Flash$104.6$0.01$10.2853m754
Math proof simplificationGemini 3.8 Flash$502.6$0.00$14.311h 4m995
Math proof simplificationGemini 3.8 Flash$2002.1$0.00$13.491h 24m1007
Math proof simplificationGrok 4.7$105.3$7.36$35.112h 20m230
Math proof simplificationGrok 4.7$506.5$0.00$25.682h 1m106
Math proof simplificationGrok 4.7$2002.2$9.87$24.861h 50m156
Math proof simplificationMuse Spark 1.3$1014.3$0.00$9.203h 2m198
Math proof simplificationMuse Spark 1.3$5020.5$0.01$13.804h 26m310
Math proof simplificationMuse Spark 1.3$20019.2$14.62$13.432h 26m250
Math proof simplificationMuse Wonder$1011.4$8.91$9.062h 54m140
Math proof simplificationMuse Wonder$506.7$34.90$27.356h 55m341
Math proof simplificationMuse Wonder$2003.3$29.44$23.154h 46m281
Math proof simplificationKimi K3$1016.3$3.35$64.399h 33m629
Math proof simplificationKimi K3$5011.2$10.54$26.444h 27m361
Math proof simplificationKimi K3$20015.0$23.39$31.496h 7m360
Math proof simplificationQwen3.8 Max$1023.0$2.21$7.694h 5m241
Math proof simplificationQwen3.8 Max$5015.2$3.15$10.124h 51m314
Math proof simplificationQwen3.8 Max$2000.0$11.51$14.056h 26m403
Math proof simplificationGLM 5.3$1011.7$1.43$5.753h 20m295
Math proof simplificationGLM 5.3$500.7$30.70$44.267h 40m635
Math proof simplificationGLM 5.3$2000.0$17.26$35.666h 28m529
Music transcriptionClaude Opus 5.5$1061.9$7.39$98.139h 2m315
Music transcriptionClaude Opus 5.5$5061.0$43.29$52.648h 4m501
Music transcriptionClaude Opus 5.5$20064.3$85.65$68.746h 40m311
Music transcriptionClaude Sonnet 5.5$1073.8$9.56$33.869h 44m529
Music transcriptionClaude Sonnet 5.5$5079.5$18.93$41.579h 47m439
Music transcriptionClaude Sonnet 5.5$20074.5$36.00$46.6710h 11m469
Music transcriptionClaude Fable 5.1$1028.8$5.52$28.815h 7m246
Music transcriptionClaude Fable 5.1$5047.2$25.89$173.068h 8m124
Music transcriptionClaude Fable 5.1$20028.1$37.95$127.556h 31m194
Music transcriptionClaude Haiku 5.5$100.0$8.39$4.233h 13m212
Music transcriptionClaude Haiku 5.5$500.0$24.43$7.774h 35m327
Music transcriptionClaude Haiku 5.5$2000.0$30.71$8.063h 39m360
Music transcriptionGPT-6 Astra$1049.4$7.04$58.252h 13m295
Music transcriptionGPT-6 Astra$5073.4$46.01$153.205h 43m670
Music transcriptionGPT-6 Astra$20076.7$198.68$184.259h 57m828
Music transcriptionGPT-6.1 Sol$1051.1$5.30$8.343h 27m218
Music transcriptionGPT-6.1 Sol$5035.1$13.96$7.633h 8m232
Music transcriptionGPT-6.1 Sol$20073.1$199.32$14.299h 3m373
Music transcriptionGPT-6 Luna$100.0$4.08$0.661h 22m349
Music transcriptionGPT-6 Luna$500.0$6.98$0.3036m161
Music transcriptionGPT-6 Luna$2000.0$1.63$0.741h 24m450
Music transcriptionGemini 3.8 Flash$100.0$0.00$15.071h 27m1111
Music transcriptionGemini 3.8 Flash$500.0$0.00$22.291h 48m1462
Music transcriptionGemini 3.8 Flash$2000.0$0.00$10.681h 33m807
Music transcriptionGrok 4.7$100.0$2.03$26.522h 38m155
Music transcriptionGrok 4.7$500.0$10.47$31.492h 19m87
Music transcriptionGrok 4.7$2001.6$12.18$51.612h 58m112
Music transcriptionMuse Spark 1.3$100.0$2.49$7.397h 20m208
Music transcriptionMuse Spark 1.3$500.0$3.60$12.785h 2m258
Music transcriptionMuse Spark 1.3$2000.0$66.11$19.2311h 2m339
Music transcriptionMuse Wonder$104.6$5.16$32.314h 17m364
Music transcriptionMuse Wonder$500.0$10.80$30.557h 5m387
Music transcriptionMuse Wonder$20013.3$2.70$7.294h 14m173
Music transcriptionKimi K3$102.6$9.45$54.1710h 17m484
Music transcriptionKimi K3$500.0$13.37$37.608h 1m412
Music transcriptionKimi K3$2009.5$33.08$38.7210h 8m429
Music transcriptionQwen3.8 Max$108.2$6.58$15.227h 45m424
Music transcriptionQwen3.8 Max$500.0$27.00$25.669h 7m806
Music transcriptionQwen3.8 Max$2000.0$72.00$16.399h 15m317
Music transcriptionGLM 5.3$100.0$3.60$11.336h 53m547
Music transcriptionGLM 5.3$500.0$14.96$41.068h 32m572
Music transcriptionGLM 5.3$2000.0$10.40$5.174h 30m265
OCR latent compressionClaude Opus 5.5$1026.9$9.88$70.685h 57m308
OCR latent compressionClaude Opus 5.5$5054.4$40.14$121.4410h372
OCR latent compressionClaude Opus 5.5$20082.6$137.32$97.249h 8m202
OCR latent compressionClaude Sonnet 5.5$1055.8$9.90$30.387h 24m274
OCR latent compressionClaude Sonnet 5.5$5067.5$42.52$61.9411h 5m649
OCR latent compressionClaude Sonnet 5.5$20063.9$198.87$60.258h 7m616
OCR latent compressionClaude Fable 5.1$1056.1$9.66$162.106h 58m200
OCR latent compressionClaude Fable 5.1$5067.9$39.36$199.567h 38m150
OCR latent compressionClaude Fable 5.1$20067.8$76.49$183.847h 54m301
OCR latent compressionClaude Haiku 5.5$108.6$9.02$6.163h 17m246
OCR latent compressionClaude Haiku 5.5$5013.8$35.78$14.019h 20m440
OCR latent compressionClaude Haiku 5.5$20030.1$173.78$11.146h 3m401
OCR latent compressionGPT-6 Astra$1036.4$8.78$73.283h 15m371
OCR latent compressionGPT-6 Astra$5057.5$45.37$133.095h 50m618
OCR latent compressionGPT-6 Astra$20064.1$150.20$242.8710h 7m1162
OCR latent compressionGPT-6.1 Sol$1037.6$9.94$13.986h 29m419
OCR latent compressionGPT-6.1 Sol$5043.7$34.90$11.907h 10m333
OCR latent compressionGPT-6.1 Sol$20035.2$125.64$10.288h 2m352
OCR latent compressionGPT-6 Luna$102.1$8.63$1.372h 38m708
OCR latent compressionGPT-6 Luna$500.4$5.76$0.581h 14m347
OCR latent compressionGPT-6 Luna$2000.7$27.92$0.471h 20m293
OCR latent compressionGemini 3.8 Flash$102.2$0.00$39.763h 48m2881
OCR latent compressionGemini 3.8 Flash$500.0$0.90$14.292h 3m1010
OCR latent compressionGemini 3.8 Flash$2000.8$7.18$21.093h 37m1598
OCR latent compressionGrok 4.7$1026.1$1.24$49.143h 36m173
OCR latent compressionGrok 4.7$504.9$20.94$54.894h 26m141
OCR latent compressionGrok 4.7$2004.8$41.88$31.694h 9m188
OCR latent compressionMuse Spark 1.3$100.0$5.40$24.0611h 58m556
OCR latent compressionMuse Spark 1.3$500.0$6.08$20.7312h457
OCR latent compressionMuse Spark 1.3$2000.0$46.38$24.7612h383
OCR latent compressionMuse Wonder$1015.3$8.63$6.642h 41m131
OCR latent compressionMuse Wonder$503.3$5.40$20.639h 8m272
OCR latent compressionMuse Wonder$2001.9$41.88$27.889h 7m296
OCR latent compressionKimi K3$107.1$9.98$80.0010h 49m702
OCR latent compressionKimi K3$5015.5$14.85$92.6910h 32m574
OCR latent compressionKimi K3$2000.0$72.68$84.3711h 26m559
OCR latent compressionQwen3.8 Max$106.6$4.42$15.387h 50m293
OCR latent compressionQwen3.8 Max$504.6$28.80$17.647h 46m532
OCR latent compressionQwen3.8 Max$2005.3$41.88$37.5312h336
OCR latent compressionGLM 5.3$104.2$8.91$45.698h 7m604
OCR latent compressionGLM 5.3$506.3$42.42$22.4212h1092
OCR latent compressionGLM 5.3$2005.7$33.56$10.599h 39m521
PII redactionClaude Opus 5.5$1073.1$8.22$19.243h 53m225
PII redactionClaude Opus 5.5$5077.3$25.87$20.643h 13m251
PII redactionClaude Opus 5.5$20077.9$175.11$20.803h 12m251
PII redactionClaude Sonnet 5.5$1070.6$5.86$31.126h 59m523
PII redactionClaude Sonnet 5.5$5072.2$36.43$32.407h 13m432
PII redactionClaude Sonnet 5.5$20068.4$103.55$27.926h 24m678
PII redactionClaude Fable 5.1$1074.8$7.47$44.323h 13m173
PII redactionClaude Fable 5.1$5070.0$34.56$34.122h 19m138
PII redactionClaude Fable 5.1$20071.3$115.52$28.182h 56m230
PII redactionClaude Haiku 5.5$1064.3$4.61$6.373h 4m294
PII redactionClaude Haiku 5.5$5058.9$12.40$6.782h 56m305
PII redactionClaude Haiku 5.5$20069.4$22.59$8.504h 25m370
PII redactionGPT-6 Astra$1064.8$3.49$26.0049m147
PII redactionGPT-6 Astra$5068.0$24.22$41.621h 26m202
PII redactionGPT-6 Astra$20059.0$10.95$18.0441m92
PII redactionGPT-6.1 Sol$1060.5$5.76$4.271h 13m150
PII redactionGPT-6.1 Sol$5064.3$12.30$8.302h 37m230
PII redactionGPT-6.1 Sol$20055.7$14.39$5.411h 46m197
PII redactionGPT-6 Luna$1021.8$3.49$0.2620m142
PII redactionGPT-6 Luna$5018.5$0.00$0.3037m142
PII redactionGPT-6 Luna$20017.4$0.00$0.1817m99
PII redactionGemini 3.8 Flash$1034.8$0.12$17.901h 19m1239
PII redactionGemini 3.8 Flash$5049.8$0.45$8.811h 8m614
PII redactionGemini 3.8 Flash$20033.8$3.49$6.051h 1m434
PII redactionGrok 4.7$1043.8$0.95$21.991h 53m93
PII redactionGrok 4.7$500.0$12.22$17.801h 20m112
PII redactionGrok 4.7$20031.5$4.71$22.781h 48m155
PII redactionMuse Spark 1.3$100.0$4.05$28.137h 57m552
PII redactionMuse Spark 1.3$5035.0$24.79$24.7310h 53m491
PII redactionMuse Spark 1.3$20041.1$11.51$6.941h 14m171
PII redactionMuse Wonder$1067.3$1.80$11.772h 55m189
PII redactionMuse Wonder$5039.3$2.80$13.283h 3m235
PII redactionMuse Wonder$20063.4$3.15$19.013h 40m289
PII redactionKimi K3$1036.3$8.31$83.5511h 9m532
PII redactionKimi K3$5056.1$31.41$23.144h 20m317
PII redactionKimi K3$20065.5$24.34$36.945h 27m343
PII redactionQwen3.8 Max$1052.6$4.63$9.524h 50m210
PII redactionQwen3.8 Max$5057.9$17.20$11.845h 19m249
PII redactionQwen3.8 Max$20052.5$23.02$39.095h 17m765
PII redactionGLM 5.3$1051.0$7.43$4.464h 9m206
PII redactionGLM 5.3$5039.6$5.94$23.653h 49m356
PII redactionGLM 5.3$20064.6$16.35$23.704h 19m357
Pokémon Random BattleClaude Opus 5.5$100.0$2.91$40.023h 15m291
Pokémon Random BattleClaude Opus 5.5$507.4$21.33$56.344h 59m473
Pokémon Random BattleClaude Opus 5.5$2002.7$111.20$68.274h 33m401
Pokémon Random BattleClaude Sonnet 5.5$100.0$3.32$38.548h 42m507
Pokémon Random BattleClaude Sonnet 5.5$5011.9$25.37$35.146h 10m497
Pokémon Random BattleClaude Sonnet 5.5$2000.0$32.82$25.504h 1m501
Pokémon Random BattleClaude Fable 5.1$100.1$1.30$35.453h 30m238
Pokémon Random BattleClaude Fable 5.1$501.0$13.47$40.682h 41m153
Pokémon Random BattleClaude Fable 5.1$2001.5$14.29$69.932h 55m85
Pokémon Random BattleClaude Haiku 5.5$101.1$2.65$7.083h 32m291
Pokémon Random BattleClaude Haiku 5.5$500.0$4.68$5.082h 47m229
Pokémon Random BattleClaude Haiku 5.5$2000.0$1.60$6.892h 38m278
Pokémon Random BattleGPT-6 Astra$106.4$5.54$181.136h 36m824
Pokémon Random BattleGPT-6 Astra$507.2$49.78$267.8210h 54m1301
Pokémon Random BattleGPT-6 Astra$2003.1$55.47$156.096h 22m640
Pokémon Random BattleGPT-6.1 Sol$100.0$0.77$8.213h 34m225
Pokémon Random BattleGPT-6.1 Sol$501.8$3.45$23.0810h 22m564
Pokémon Random BattleGPT-6.1 Sol$2000.0$169.36$19.039h 16m486
Pokémon Random BattleGPT-6 Luna$100.0$0.00$0.3337m170
Pokémon Random BattleGPT-6 Luna$500.0$0.00$0.2735m139
Pokémon Random BattleGPT-6 Luna$2000.0$0.00$0.3431m178
Pokémon Random BattleGemini 3.8 Flash$100.0$0.00$8.3938m586
Pokémon Random BattleGemini 3.8 Flash$500.0$0.00$8.5644m598
Pokémon Random BattleGemini 3.8 Flash$2000.0$0.00$6.8352m474
Pokémon Random BattleGrok 4.7$100.0$0.00$20.051h 26m235
Pokémon Random BattleGrok 4.7$500.0$3.04$31.672h 29m193
Pokémon Random BattleGrok 4.7$2000.0$0.00$28.792h 2m120
Pokémon Random BattleMuse Spark 1.3$100.0$2.06$15.024h 16m368
Pokémon Random BattleMuse Spark 1.3$500.0$2.13$18.622h 19m388
Pokémon Random BattleMuse Spark 1.3$2000.0$7.82$25.626h 10m554
Pokémon Random BattleMuse Wonder$100.0$0.32$15.805h 9m235
Pokémon Random BattleMuse Wonder$500.0$0.36$16.132h 54m203
Pokémon Random BattleMuse Wonder$2000.0$0.83$11.002h 50m174
Pokémon Random BattleKimi K3$100.0$1.97$63.718h 11m581
Pokémon Random BattleKimi K3$500.0$17.84$55.466h 35m529
Pokémon Random BattleKimi K3$2000.0$21.23$90.5511h 9m715
Pokémon Random BattleQwen3.8 Max$100.0$0.34$8.404h 2m273
Pokémon Random BattleQwen3.8 Max$500.0$0.49$18.778h 38m505
Pokémon Random BattleQwen3.8 Max$2000.0$2.63$10.435h 7m297
Pokémon Random BattleGLM 5.3$100.0$3.49$11.894h 50m616
Pokémon Random BattleGLM 5.3$500.0$1.86$16.087h 40m756
Pokémon Random BattleGLM 5.3$2000.0$0.49$9.394h 40m445
Screenshot diffingClaude Opus 5.5$1026.8$8.56$31.003h 25m307
Screenshot diffingClaude Opus 5.5$5034.4$41.69$57.487h 8m296
Screenshot diffingClaude Opus 5.5$20038.0$172.35$69.506h 19m354
Screenshot diffingClaude Sonnet 5.5$1029.7$6.82$23.284h 43m355
Screenshot diffingClaude Sonnet 5.5$5033.5$43.14$20.084h 43m269
Screenshot diffingClaude Sonnet 5.5$20035.2$121.33$33.975h 48m582
Screenshot diffingClaude Fable 5.1$1031.1$9.80$56.003h 24m112
Screenshot diffingClaude Fable 5.1$5023.2$29.38$26.273h 4m227
Screenshot diffingClaude Fable 5.1$20046.4$150.36$117.005h 46m225
Screenshot diffingClaude Haiku 5.5$1019.2$9.20$5.002h 50m239
Screenshot diffingClaude Haiku 5.5$5029.6$34.64$11.507h 5m294
Screenshot diffingClaude Haiku 5.5$20038.5$70.65$8.715h 21m360
Screenshot diffingGPT-6 Astra$1016.0$6.98$40.791h 23m230
Screenshot diffingGPT-6 Astra$5015.5$13.96$40.561h 12m213
Screenshot diffingGPT-6 Astra$2008.2$33.57$48.881h 56m230
Screenshot diffingGPT-6.1 Sol$106.2$5.82$4.181h 38m132
Screenshot diffingGPT-6.1 Sol$5010.2$17.26$7.172h 27m229
Screenshot diffingGPT-6.1 Sol$20010.5$27.98$8.103h 2m244
Screenshot diffingGPT-6 Luna$106.9$6.24$0.691h 32m354
Screenshot diffingGPT-6 Luna$504.6$13.96$0.851h 50m429
Screenshot diffingGPT-6 Luna$2002.9$25.47$1.213h 19m742
Screenshot diffingGemini 3.8 Flash$100.0$0.14$9.351h 7m684
Screenshot diffingGemini 3.8 Flash$500.0$0.01$7.111h 2m570
Screenshot diffingGemini 3.8 Flash$2000.0$0.05$7.641h 17m495
Screenshot diffingGrok 4.7$100.0$6.92$29.042h 14m59
Screenshot diffingGrok 4.7$508.8$10.48$26.341h 55m155
Screenshot diffingGrok 4.7$2008.0$13.97$34.782h 31m254
Screenshot diffingMuse Spark 1.3$107.9$3.60$8.174h 28m206
Screenshot diffingMuse Spark 1.3$503.4$9.00$10.795h 56m267
Screenshot diffingMuse Spark 1.3$20012.7$45.99$13.214h 23m285
Screenshot diffingMuse Wonder$1013.0$4.06$18.124h 35m265
Screenshot diffingMuse Wonder$501.6$5.41$16.918h 30m269
Screenshot diffingMuse Wonder$2006.5$42.06$25.848h 34m363
Screenshot diffingKimi K3$1017.1$9.62$16.365h 35m288
Screenshot diffingKimi K3$5019.6$44.10$24.149h 47m329
Screenshot diffingKimi K3$2000.0$82.30$62.7210h 35m537
Screenshot diffingQwen3.8 Max$109.2$9.61$17.569h 31m418
Screenshot diffingQwen3.8 Max$502.9$28.33$14.646h 22m347
Screenshot diffingQwen3.8 Max$2008.7$109.83$20.138h 55m438
Screenshot diffingGLM 5.3$1011.6$9.47$18.798h 22m922
Screenshot diffingGLM 5.3$500.0$34.98$12.707h 55m572
Screenshot diffingGLM 5.3$2000.0$144.70$10.717h 43m566
Screenshot generationClaude Opus 5.5$1074.2$8.55$78.357h 3m273
Screenshot generationClaude Opus 5.5$5063.0$19.37$40.514h 50m408
Screenshot generationClaude Opus 5.5$20078.9$50.15$65.905h 51m352
Screenshot generationClaude Sonnet 5.5$1057.8$7.80$36.387h 42m811
Screenshot generationClaude Sonnet 5.5$5059.7$30.73$38.578h 53m518
Screenshot generationClaude Sonnet 5.5$20064.6$58.14$44.2610h 35m936
Screenshot generationClaude Fable 5.1$1044.6$5.56$47.202h 46m226
Screenshot generationClaude Fable 5.1$500.0$19.00$45.562h 34m254
Screenshot generationClaude Fable 5.1$20035.0$32.00$46.102h 55m221
Screenshot generationClaude Haiku 5.5$1035.9$6.75$5.623h 31m286
Screenshot generationClaude Haiku 5.5$5021.6$5.82$5.071h 53m244
Screenshot generationClaude Haiku 5.5$20040.6$14.33$3.662h 50m202
Screenshot generationGPT-6 Astra$1047.3$6.11$43.741h 17m222
Screenshot generationGPT-6 Astra$5059.3$22.70$163.705h 47m785
Screenshot generationGPT-6 Astra$20050.6$22.32$36.471h 18m196
Screenshot generationGPT-6.1 Sol$1030.1$7.28$8.092h 17m282
Screenshot generationGPT-6.1 Sol$5040.5$13.98$5.161h 42m198
Screenshot generationGPT-6.1 Sol$20042.1$14.01$9.783h 8m347
Screenshot generationGPT-6 Luna$1014.1$0.00$0.0610m43
Screenshot generationGPT-6 Luna$5016.5$0.00$0.1420m87
Screenshot generationGPT-6 Luna$20021.0$0.00$0.1023m84
Screenshot generationGemini 3.8 Flash$108.6$0.02$13.0359m888
Screenshot generationGemini 3.8 Flash$5016.2$0.32$6.5240m494
Screenshot generationGemini 3.8 Flash$2000.0$0.47$7.541h 5m547
Screenshot generationGrok 4.7$1028.6$7.02$20.241h 14m96
Screenshot generationGrok 4.7$5021.1$11.39$16.041h 4m74
Screenshot generationGrok 4.7$20017.9$27.93$30.091h 56m158
Screenshot generationMuse Spark 1.3$1016.8$3.62$22.394h 5m435
Screenshot generationMuse Spark 1.3$500.0$5.24$11.492h 44m270
Screenshot generationMuse Spark 1.3$20019.8$7.53$28.815h 10m494
Screenshot generationMuse Wonder$1032.5$1.71$17.263h 17m232
Screenshot generationMuse Wonder$5022.4$14.03$13.502h 20m175
Screenshot generationMuse Wonder$20018.6$18.92$22.813h 34m273
Screenshot generationKimi K3$1032.7$4.86$97.787h 35m583
Screenshot generationKimi K3$500.0$18.13$63.579h 2m480
Screenshot generationKimi K3$20035.2$7.69$74.526h 40m588
Screenshot generationQwen3.8 Max$1024.9$0.90$7.962h 51m238
Screenshot generationQwen3.8 Max$5029.6$1.01$7.763h 13m225
Screenshot generationQwen3.8 Max$20032.1$4.83$12.443h 22m444
Screenshot generationGLM 5.3$100.0$1.86$24.937h 57m1183
Screenshot generationGLM 5.3$500.0$14.07$66.215h 28m958
Screenshot generationGLM 5.3$20032.7$1.94$124.797h 52m1692
Speculative draftingClaude Opus 5.5$1021.2$9.38$40.304h 38m204
Speculative draftingClaude Opus 5.5$5037.0$39.11$64.387h 10m223
Speculative draftingClaude Opus 5.5$20041.8$175.20$56.647h 10m228
Speculative draftingClaude Sonnet 5.5$1020.8$9.90$22.776h 48m265
Speculative draftingClaude Sonnet 5.5$5033.8$45.53$29.417h 49m389
Speculative draftingClaude Sonnet 5.5$20048.4$176.61$41.939h 26m483
Speculative draftingClaude Fable 5.1$1015.6$9.90$105.275h 59m108
Speculative draftingClaude Fable 5.1$5026.8$31.41$84.545h 16m116
Speculative draftingClaude Fable 5.1$20029.5$82.67$199.709h 7m200
Speculative draftingClaude Haiku 5.5$105.5$6.18$7.564h 56m344
Speculative draftingClaude Haiku 5.5$5018.6$19.20$5.654h 22m282
Speculative draftingClaude Haiku 5.5$20021.3$47.47$9.597h 3m435
Speculative draftingGPT-6 Astra$1016.8$9.89$64.982h 57m341
Speculative draftingGPT-6 Astra$5016.5$36.16$150.727h 55m752
Speculative draftingGPT-6 Astra$20025.8$191.58$184.709h 48m895
Speculative draftingGPT-6.1 Sol$108.1$8.63$5.943h 2m190
Speculative draftingGPT-6.1 Sol$500.0$45.37$9.407h 56m266
Speculative draftingGPT-6.1 Sol$20025.2$150.84$10.6910h 8m283
Speculative draftingGPT-6 Luna$100.0$3.49$0.1422m94
Speculative draftingGPT-6 Luna$500.0$1.49$0.2134m145
Speculative draftingGPT-6 Luna$2000.0$2.88$0.2643m167
Speculative draftingGemini 3.8 Flash$100.0$0.00$5.4134m435
Speculative draftingGemini 3.8 Flash$500.0$2.98$6.121h 23m409
Speculative draftingGemini 3.8 Flash$2000.0$8.73$17.982h 6m1290
Speculative draftingGrok 4.7$100.0$9.75$30.702h 52m76
Speculative draftingGrok 4.7$500.0$34.90$33.773h 2m123
Speculative draftingGrok 4.7$2000.0$22.28$61.315h 51m62
Speculative draftingMuse Spark 1.3$100.0$4.50$11.619h 49m272
Speculative draftingMuse Spark 1.3$500.0$34.52$15.138h 50m307
Speculative draftingMuse Spark 1.3$2008.7$34.52$13.156h 49m270
Speculative draftingMuse Wonder$109.5$8.91$12.174h 34m189
Speculative draftingMuse Wonder$5013.1$38.39$15.865h 17m228
Speculative draftingMuse Wonder$2005.2$34.52$14.649h 11m230
Speculative draftingKimi K3$100.0$9.99$11.044h 15m197
Speculative draftingKimi K3$509.9$34.52$18.909h 11m302
Speculative draftingKimi K3$2000.0$38.39$27.9210h 30m398
Speculative draftingQwen3.8 Max$100.0$9.06$13.297h 45m245
Speculative draftingQwen3.8 Max$500.0$22.20$18.6110h 19m288
Speculative draftingQwen3.8 Max$2007.0$143.21$13.885h 47m285
Speculative draftingGLM 5.3$100.0$9.99$12.184h 44m535
Speculative draftingGLM 5.3$5012.0$32.32$10.278h 46m502
Speculative draftingGLM 5.3$20013.7$31.65$26.788h 18m354
SVG generationClaude Opus 5.5$100.0$9.88$23.673h 28m178
SVG generationClaude Opus 5.5$505.2$45.64$23.125h 52m267
SVG generationClaude Opus 5.5$20018.0$179.04$67.379h 32m312
SVG generationClaude Sonnet 5.5$100.0$9.79$21.794h 13m247
SVG generationClaude Sonnet 5.5$508.2$49.24$19.435h 25m450
SVG generationClaude Sonnet 5.5$20013.9$183.81$29.588h 51m420
SVG generationClaude Fable 5.1$102.7$7.84$57.303h 17m153
SVG generationClaude Fable 5.1$502.0$49.82$191.529h 1m209
SVG generationClaude Fable 5.1$20020.3$174.13$129.966h 42m153
SVG generationClaude Haiku 5.5$100.0$8.00$6.384h 1m213
SVG generationClaude Haiku 5.5$5010.0$36.68$9.246h 10m288
SVG generationClaude Haiku 5.5$20010.1$160.62$11.898h 1m514
SVG generationGPT-6 Astra$100.0$10.00$66.292h 55m397
SVG generationGPT-6 Astra$508.3$49.76$122.845h 44m660
SVG generationGPT-6 Astra$20014.0$199.93$188.718h 56m961
SVG generationGPT-6.1 Sol$103.2$8.47$5.461h 50m189
SVG generationGPT-6.1 Sol$507.2$49.95$13.565h 44m431
SVG generationGPT-6.1 Sol$2000.0$199.93$20.8810h 1m664
SVG generationGPT-6 Luna$100.0$6.69$0.861h 51m536
SVG generationGPT-6 Luna$500.0$7.72$0.521h 8m344
SVG generationGPT-6 Luna$2000.0$35.20$2.075h 52m1281
SVG generationGemini 3.8 Flash$105.3$0.05$13.102h 18m946
SVG generationGemini 3.8 Flash$500.0$5.82$14.1412h854
SVG generationGemini 3.8 Flash$2000.0$8.73$6.691h 18m453
SVG generationGrok 4.7$100.0$9.41$19.172h 10m109
SVG generationGrok 4.7$500.0$15.68$46.799h 54m88
SVG generationGrok 4.7$2000.0$57.53$28.394h 5m114
SVG generationMuse Spark 1.3$100.0$9.51$15.158h 1m295
SVG generationMuse Spark 1.3$500.0$23.27$6.264h 32m173
SVG generationMuse Spark 1.3$2000.0$92.78$11.488h 28m254
SVG generationMuse Wonder$100.0$8.91$18.626h 16m238
SVG generationMuse Wonder$500.0$21.39$25.7310h 1m319
SVG generationMuse Wonder$2000.0$35.87$7.704h 13m171
SVG generationKimi K3$100.0$9.89$24.193h 10m195
SVG generationKimi K3$500.0$48.45$40.228h 37m349
SVG generationKimi K3$2000.0$84.47$40.999h 59m373
SVG generationQwen3.8 Max$100.0$8.26$12.716h 37m266
SVG generationQwen3.8 Max$500.0$40.87$17.339h 41m330
SVG generationQwen3.8 Max$2000.0$167.80$17.177h 10m360
SVG generationGLM 5.3$100.0$8.65$15.473h 18m243
SVG generationGLM 5.3$500.0$49.43$40.688h 43m543
SVG generationGLM 5.3$2000.0$92.83$27.6811h 40m441
Ternary quantizationClaude Opus 5.5$1022.7$8.49$36.534h 46m275
Ternary quantizationClaude Opus 5.5$5036.5$46.06$93.369h 57m284
Ternary quantizationClaude Opus 5.5$20049.1$195.44$26.907h 11m338
Ternary quantizationClaude Sonnet 5.5$1024.7$9.03$41.575h 43m807
Ternary quantizationClaude Sonnet 5.5$5018.9$35.89$42.0410h 34m457
Ternary quantizationClaude Sonnet 5.5$20041.2$192.65$42.307h 46m790
Ternary quantizationClaude Fable 5.1$107.7$9.83$46.913h 20m148
Ternary quantizationClaude Fable 5.1$5029.3$31.41$97.285h 46m200
Ternary quantizationClaude Fable 5.1$20028.9$73.29$263.429h 15m206
Ternary quantizationClaude Haiku 5.5$108.7$8.73$4.212h 43m199
Ternary quantizationClaude Haiku 5.5$501.2$34.32$14.537h 29m482
Ternary quantizationClaude Haiku 5.5$2007.9$106.34$22.379h 42m360
Ternary quantizationGPT-6 Astra$101.3$9.89$58.532h 30m322
Ternary quantizationGPT-6 Astra$500.2$49.98$187.077h 23m863
Ternary quantizationGPT-6 Astra$20019.5$136.11$177.9110h 6m848
Ternary quantizationGPT-6.1 Sol$101.5$4.69$4.961h 23m191
Ternary quantizationGPT-6.1 Sol$502.1$38.39$10.918h 48m391
Ternary quantizationGPT-6.1 Sol$2004.6$166.71$11.5210h 33m316
Ternary quantizationGPT-6 Luna$100.0$5.76$0.5458m296
Ternary quantizationGPT-6 Luna$500.0$3.49$0.3358m162
Ternary quantizationGPT-6 Luna$2000.1$8.63$0.932h 6m515
Ternary quantizationGemini 3.8 Flash$100.4$0.00$10.981h 11m818
Ternary quantizationGemini 3.8 Flash$500.0$0.00$9.8558m710
Ternary quantizationGemini 3.8 Flash$2000.0$0.00$12.861h 48m1031
Ternary quantizationGrok 4.7$100.5$8.09$37.242h 41m102
Ternary quantizationGrok 4.7$500.2$17.45$52.854h 35m179
Ternary quantizationGrok 4.7$2000.0$14.85$32.603h 25m197
Ternary quantizationMuse Spark 1.3$100.0$0.00$15.067h 5m325
Ternary quantizationMuse Spark 1.3$500.5$38.33$16.639h 39m326
Ternary quantizationMuse Spark 1.3$2009.3$70.84$20.6311h 50m359
Ternary quantizationMuse Wonder$100.0$4.50$36.3610h 16m474
Ternary quantizationMuse Wonder$500.0$17.82$24.1210h 1m306
Ternary quantizationMuse Wonder$2000.2$73.29$26.188h 5m287
Ternary quantizationKimi K3$105.5$9.99$31.578h 19m371
Ternary quantizationKimi K3$500.0$40.04$64.3911h 25m634
Ternary quantizationKimi K3$2001.4$60.41$29.467h 5m356
Ternary quantizationQwen3.8 Max$102.5$8.91$36.846h375
Ternary quantizationQwen3.8 Max$505.4$49.45$12.595h 53m333
Ternary quantizationQwen3.8 Max$2003.7$41.88$38.659h 3m470
Ternary quantizationGLM 5.3$100.0$9.89$7.444h 31m274
Ternary quantizationGLM 5.3$5010.1$38.39$37.386h 31m520
Ternary quantizationGLM 5.3$2002.3$71.26$61.719h 20m831
Video frame interpolationClaude Opus 5.5$1091.1$8.10$57.947h 58m294
Video frame interpolationClaude Opus 5.5$5086.7$41.88$23.075h 15m289
Video frame interpolationClaude Opus 5.5$20087.8$101.21$82.479h 50m259
Video frame interpolationClaude Sonnet 5.5$1086.0$8.78$28.7510h 3m318
Video frame interpolationClaude Sonnet 5.5$5086.3$42.90$33.767h 54m378
Video frame interpolationClaude Sonnet 5.5$20093.2$130.68$34.519h 48m300
Video frame interpolationClaude Fable 5.1$1078.5$4.50$99.405h 53m107
Video frame interpolationClaude Fable 5.1$5081.8$47.70$119.286h 40m174
Video frame interpolationClaude Fable 5.1$20058.2$59.33$130.886h 43m153
Video frame interpolationClaude Haiku 5.5$1063.7$7.43$6.515h 11m332
Video frame interpolationClaude Haiku 5.5$5064.3$24.43$12.026h 17m268
Video frame interpolationClaude Haiku 5.5$20065.4$28.77$14.787h 52m422
Video frame interpolationGPT-6 Astra$1085.3$10.00$268.7910h 14m1167
Video frame interpolationGPT-6 Astra$5091.2$49.96$246.868h 45m1068
Video frame interpolationGPT-6 Astra$20084.6$143.31$276.3311h 27m1157
Video frame interpolationGPT-6.1 Sol$1087.8$9.75$17.9710h 1m454
Video frame interpolationGPT-6.1 Sol$5072.0$31.65$16.1710h 26m478
Video frame interpolationGPT-6.1 Sol$20086.5$149.67$21.199h 56m600
Video frame interpolationGPT-6 Luna$100.0$6.99$0.901h 19m469
Video frame interpolationGPT-6 Luna$500.0$5.40$1.262h 54m663
Video frame interpolationGPT-6 Luna$20025.7$83.76$1.894h 49m1044
Video frame interpolationGemini 3.8 Flash$100.0$0.00$5.4930m397
Video frame interpolationGemini 3.8 Flash$507.1$0.00$2.2520m211
Video frame interpolationGemini 3.8 Flash$2000.0$0.00$3.4333m263
Video frame interpolationGrok 4.7$100.0$1.35$13.291h 12m171
Video frame interpolationGrok 4.7$500.0$17.45$21.171h 43m181
Video frame interpolationGrok 4.7$2000.0$2.70$13.6952m188
Video frame interpolationMuse Spark 1.3$1023.7$5.40$9.613h 21m242
Video frame interpolationMuse Spark 1.3$5049.8$4.50$14.206h 8m320
Video frame interpolationMuse Spark 1.3$20031.2$66.11$11.285h 59m227
Video frame interpolationMuse Wonder$1068.8$5.85$19.945h 9m286
Video frame interpolationMuse Wonder$5049.8$5.40$12.735h 26m185
Video frame interpolationMuse Wonder$20055.9$31.21$10.823h 41m206
Video frame interpolationKimi K3$100.0$6.30$36.788h 51m477
Video frame interpolationKimi K3$5032.5$40.14$35.646h 14m282
Video frame interpolationKimi K3$20079.5$69.80$23.915h 30m330
Video frame interpolationQwen3.8 Max$1031.2$4.50$18.038h 52m286
Video frame interpolationQwen3.8 Max$500.0$13.23$13.866h 23m275
Video frame interpolationQwen3.8 Max$2000.0$64.80$17.379h 17m274
Video frame interpolationGLM 5.3$1026.9$4.05$45.906h 59m672
Video frame interpolationGLM 5.3$5045.7$7.81$35.588h 41m492
Video frame interpolationGLM 5.3$20052.3$33.57$9.749h 24m488
Vision for a ternary LMClaude Opus 5.5$100.4$4.08$25.762h 33m254
Vision for a ternary LMClaude Opus 5.5$506.5$26.39$54.885h 17m202
Vision for a ternary LMClaude Opus 5.5$2002.4$111.68$43.586h 58m414
Vision for a ternary LMClaude Sonnet 5.5$100.0$5.41$17.282h 37m312
Vision for a ternary LMClaude Sonnet 5.5$500.0$18.43$21.563h 35m342
Vision for a ternary LMClaude Sonnet 5.5$2000.0$174.17$46.677h 7m667
Vision for a ternary LMClaude Fable 5.1$100.0$7.20$62.002h 51m74
Vision for a ternary LMClaude Fable 5.1$500.0$14.42$48.862h 55m135
Vision for a ternary LMClaude Fable 5.1$2000.0$52.35$68.564h 8m161
Vision for a ternary LMClaude Haiku 5.5$100.0$7.20$5.142h 24m230
Vision for a ternary LMClaude Haiku 5.5$500.0$14.39$7.153h 13m194
Vision for a ternary LMClaude Haiku 5.5$2000.0$48.86$8.113h 53m310
Vision for a ternary LMGPT-6 Astra$100.0$8.91$122.175h 17m548
Vision for a ternary LMGPT-6 Astra$500.0$49.24$209.878h 7m999
Vision for a ternary LMGPT-6 Astra$2000.0$101.58$131.385h 13m592
Vision for a ternary LMGPT-6.1 Sol$100.0$9.96$7.783h 6m238
Vision for a ternary LMGPT-6.1 Sol$500.0$43.47$16.937h 41m501
Vision for a ternary LMGPT-6.1 Sol$2000.0$112.83$13.7710h 19m400
Vision for a ternary LMGPT-6 Luna$100.0$8.15$0.671h 46m369
Vision for a ternary LMGPT-6 Luna$500.0$37.81$1.999h1178
Vision for a ternary LMGPT-6 Luna$2000.0$34.90$0.581h 11m307
Vision for a ternary LMGemini 3.8 Flash$100.0$0.00$18.822h 33m1183
Vision for a ternary LMGemini 3.8 Flash$500.0$0.00$13.451h 43m933
Vision for a ternary LMGemini 3.8 Flash$2000.0$0.00$10.432h 12m598
Vision for a ternary LMGrok 4.7$100.0$8.78$30.412h 22m168
Vision for a ternary LMGrok 4.7$500.0$8.91$38.273h 40m61
Vision for a ternary LMGrok 4.7$2000.0$27.92$33.572h 37m200
Vision for a ternary LMMuse Spark 1.3$100.0$9.99$13.726h 39m276
Vision for a ternary LMMuse Spark 1.3$500.0$34.52$19.6011h 35m393
Vision for a ternary LMMuse Spark 1.3$2000.0$114.60$29.0911h 49m558
Vision for a ternary LMMuse Wonder$100.0$9.66$19.825h 29m245
Vision for a ternary LMMuse Wonder$500.0$31.41$18.176h 5m216
Vision for a ternary LMMuse Wonder$2000.0$31.65$15.259h 55m234
Vision for a ternary LMKimi K3$100.0$8.63$13.682h 52m176
Vision for a ternary LMKimi K3$500.0$27.99$23.947h 1m333
Vision for a ternary LMKimi K3$2000.0$41.93$79.958h 7m637
Vision for a ternary LMQwen3.8 Max$100.0$9.83$14.566h 26m296
Vision for a ternary LMQwen3.8 Max$500.0$27.92$9.244h 22m230
Vision for a ternary LMQwen3.8 Max$2000.0$31.66$21.659h 55m464
Vision for a ternary LMGLM 5.3$100.0$8.63$27.173h 6m233
Vision for a ternary LMGLM 5.3$500.0$18.83$49.678h 16m632
Vision for a ternary LMGLM 5.3$2000.0$31.65$13.2610h 42m601
Voice endpointingClaude Opus 5.5$1074.7$1.80$27.013h 14m210
Voice endpointingClaude Opus 5.5$5068.8$6.73$52.644h 59m250
Voice endpointingClaude Opus 5.5$20055.8$34.90$28.775h 3m336
Voice endpointingClaude Sonnet 5.5$1049.4$0.98$12.401h 41m241
Voice endpointingClaude Sonnet 5.5$5046.1$5.40$21.544h 41m439
Voice endpointingClaude Sonnet 5.5$20057.4$5.94$16.523h 36m319
Voice endpointingClaude Fable 5.1$1065.0$3.90$83.074h 40m137
Voice endpointingClaude Fable 5.1$500.0$2.70$45.103h 1m152
Voice endpointingClaude Fable 5.1$20050.7$27.92$24.561h 47m107
Voice endpointingClaude Haiku 5.5$1033.6$0.00$7.754h 11m274
Voice endpointingClaude Haiku 5.5$503.7$20.94$7.313h 49m312
Voice endpointingClaude Haiku 5.5$20019.9$20.94$13.596h 19m249
Voice endpointingGPT-6 Astra$1050.5$1.80$27.6056m171
Voice endpointingGPT-6 Astra$5062.9$13.96$20.6237m108
Voice endpointingGPT-6 Astra$20060.4$10.47$24.6850m119
Voice endpointingGPT-6.1 Sol$1045.8$1.80$3.821h 18m161
Voice endpointingGPT-6.1 Sol$500.0$13.96$3.351h 5m120
Voice endpointingGPT-6.1 Sol$20042.3$37.99$7.492h 26m241
Voice endpointingGPT-6 Luna$1029.0$0.00$0.1716m119
Voice endpointingGPT-6 Luna$5032.4$0.00$0.1218m71
Voice endpointingGPT-6 Luna$20043.7$0.00$0.471h251
Voice endpointingGemini 3.8 Flash$1040.0$0.00$8.1724m510
Voice endpointingGemini 3.8 Flash$500.0$0.00$4.9641m364
Voice endpointingGemini 3.8 Flash$2000.0$0.00$4.951h 21m290
Voice endpointingGrok 4.7$1043.3$2.97$10.9650m147
Voice endpointingGrok 4.7$500.0$24.43$21.391h 40m133
Voice endpointingGrok 4.7$2000.0$1.80$15.461h 17m54
Voice endpointingMuse Spark 1.3$1034.1$5.40$17.334h 32m309
Voice endpointingMuse Spark 1.3$500.0$3.60$10.192h 59m224
Voice endpointingMuse Spark 1.3$2000.0$6.75$17.357h 49m339
Voice endpointingMuse Wonder$100.0$1.79$16.092h 57m189
Voice endpointingMuse Wonder$505.2$4.05$19.983h 41m250
Voice endpointingMuse Wonder$2000.0$4.05$19.335h 56m243
Voice endpointingKimi K3$100.0$4.95$33.488h 23m365
Voice endpointingKimi K3$500.0$18.73$20.804h 55m273
Voice endpointingKimi K3$2000.0$47.61$50.879h 31m529
Voice endpointingQwen3.8 Max$1050.5$3.60$11.145h 37m308
Voice endpointingQwen3.8 Max$5033.2$15.60$13.776h 26m263
Voice endpointingQwen3.8 Max$2000.0$11.88$18.475h 27m319
Voice endpointingGLM 5.3$1040.8$4.13$10.677h 9m502
Voice endpointingGLM 5.3$500.0$1.03$12.227h 37m606
Voice endpointingGLM 5.3$2000.0$33.08$21.588h 3m615
Zero-shot classificationClaude Opus 5.5$1059.3$8.95$16.203h 13m191
Zero-shot classificationClaude Opus 5.5$5057.7$14.11$33.363h 32m208
Zero-shot classificationClaude Opus 5.5$20059.0$47.38$56.425h 42m369
Zero-shot classificationClaude Sonnet 5.5$1062.0$6.99$24.633h 22m337
Zero-shot classificationClaude Sonnet 5.5$5063.6$34.48$20.305h 55m430
Zero-shot classificationClaude Sonnet 5.5$2000.0$87.99$50.937h 20m649
Zero-shot classificationClaude Fable 5.1$1059.6$9.60$91.765h 2m115
Zero-shot classificationClaude Fable 5.1$500.0$44.98$162.488h 2m140
Zero-shot classificationClaude Fable 5.1$20062.1$47.64$76.745h182
Zero-shot classificationClaude Haiku 5.5$1052.3$5.88$6.813h 9m272
Zero-shot classificationClaude Haiku 5.5$5057.4$23.01$8.764h 57m368
Zero-shot classificationClaude Haiku 5.5$20048.1$30.10$7.445h 20m330
Zero-shot classificationGPT-6 Astra$1052.5$5.24$20.4539m110
Zero-shot classificationGPT-6 Astra$5047.8$11.51$33.991h 17m210
Zero-shot classificationGPT-6 Astra$20046.7$13.96$18.6946m98
Zero-shot classificationGPT-6.1 Sol$1038.7$5.29$4.921h 52m184
Zero-shot classificationGPT-6.1 Sol$5050.2$18.05$7.983h 22m176
Zero-shot classificationGPT-6.1 Sol$20056.5$30.50$5.072h 46m129
Zero-shot classificationGPT-6 Luna$1036.9$3.09$0.571h 52m387
Zero-shot classificationGPT-6 Luna$5029.4$13.96$0.411h 23m208
Zero-shot classificationGPT-6 Luna$20024.8$6.98$0.3627m181
Zero-shot classificationGemini 3.8 Flash$100.0$0.00$3.8556m263
Zero-shot classificationGemini 3.8 Flash$500.0$0.00$31.561h 46m2088
Zero-shot classificationGemini 3.8 Flash$20029.6$0.00$5.6752m386
Zero-shot classificationGrok 4.7$100.0$6.98$15.401h 19m207
Zero-shot classificationGrok 4.7$5031.0$5.94$15.201h 3m181
Zero-shot classificationGrok 4.7$20017.4$14.19$8.3043m138
Zero-shot classificationMuse Spark 1.3$1026.7$7.27$13.324h 32m300
Zero-shot classificationMuse Spark 1.3$500.0$24.70$8.255h 1m234
Zero-shot classificationMuse Spark 1.3$20043.2$9.82$6.951h 58m166
Zero-shot classificationMuse Wonder$1048.6$2.25$11.282h 48m164
Zero-shot classificationMuse Wonder$5016.0$17.45$5.242h129
Zero-shot classificationMuse Wonder$20037.1$14.85$12.515h 56m180
Zero-shot classificationKimi K3$1041.2$6.38$17.023h 17m245
Zero-shot classificationKimi K3$5040.2$28.31$17.626h 15m267
Zero-shot classificationKimi K3$2000.0$13.96$13.333h 42m222
Zero-shot classificationQwen3.8 Max$100.0$9.90$13.817h 41m253
Zero-shot classificationQwen3.8 Max$5043.2$19.43$8.884h 56m272
Zero-shot classificationQwen3.8 Max$20040.4$19.16$14.188h 28m293
Zero-shot classificationGLM 5.3$1013.8$4.12$14.753h 10m204
Zero-shot classificationGLM 5.3$5041.1$28.48$29.185h 16m429
Zero-shot classificationGLM 5.3$2000.0$62.37$30.526h 17m466