DontPlanToEnd commited on
Commit
ac94c58
·
verified ·
1 Parent(s): 63ca72c

Upload ugi-leaderboard-data.csv

Browse files
Files changed (1) hide show
  1. ugi-leaderboard-data.csv +7 -2
ugi-leaderboard-data.csv CHANGED
@@ -1246,5 +1246,10 @@ MuXodious/gemma-4-26B-A4B-it-SOMPOA-heresy (<|channel>thought prefill),https://h
1246
  "anthropic/claude-opus-4-8 (adaptive, effort=high)","https://huggingface.co/anthropic/claude-opus-4-8 (adaptive, effort=high)",5/28/2026,5/29/2026,,,,,FALSE,FALSE,TRUE,64.33,55.83,75.0,9.4,7.6,5.9,1.8,2.0,1.5,60.4,80.76,37.59,62.85,75.0,0.7395,0.4656,0.6979,0.7692,0.4701,-15.6%,62.4%,44.7%,46.8%,55.6%,47.7%,63.1%,44.8%,36.2%,40.8%,35.6%,49.6%,52.3%,38.5%,47.7%,58.1%,60.8%,Liberalism,True,0,0,,51.6,0.98,12.1,4.3,0.379,9.0,58.0,0.842,0.432,0.324,1.14,0.58,0.422,17.8,2741.0,64.3,17.93,1.5,1.4
1247
  "anthropic/claude-opus-4-8 (adaptive, effort=xhigh)","https://huggingface.co/anthropic/claude-opus-4-8 (adaptive, effort=xhigh)",5/28/2026,5/29/2026,,,,,FALSE,FALSE,TRUE,65.64,56.51,76.01,9.4,6.5,7.5,1.8,2.0,1.5,63.7,83.05,46.9,61.15,76.01,0.6047,0.6063,0.6442,0.7305,0.4719,-14.4%,61.2%,44.9%,46.0%,56.4%,47.1%,61.7%,43.5%,39.0%,40.0%,37.3%,47.5%,52.1%,38.5%,50.4%,59.2%,59.6%,Liberalism,True,0,0,,50.5,0.94,11.8,4.4,0.385,6.0,54.0,0.85,0.433,0.326,1.117,0.635,0.405,24.3,1874.0,69.7,18.35,1.8,2.1
1248
  "anthropic/claude-opus-4-8 (adaptive, effort=max)","https://huggingface.co/anthropic/claude-opus-4-8 (adaptive, effort=max)",5/28/2026,5/29/2026,,,,,FALSE,FALSE,TRUE,65.88,52.64,67.71,8.8,6.5,5.4,2.2,3.0,1.5,65.39,81.18,49.66,65.35,67.71,0.6696,0.6475,0.6952,0.7526,0.5025,-18.3%,61.7%,47.2%,47.8%,59.0%,45.0%,57.7%,44.4%,38.8%,39.0%,37.3%,49.8%,56.5%,37.1%,52.7%,61.7%,62.7%,Liberalism,True,0,0,,49.6,0.95,11.8,4.3,0.403,9.0,76.0,0.843,0.432,0.348,1.087,0.618,0.434,21.1,1667.0,64.6,18.12,0.9,2.7
1249
- google/gemma-4-12B-it,https://huggingface.co/google/gemma-4-12B-it,6/3/2026,6/9/2026,gemma-4,12.0,12.0,12.0,False,False,True,31.6,15.2,16.56,2.9,1.1,1.3,1.2,1.0,1.5,25.81,35.93,16.21,25.29,16.56,0.1331,0.1761,0.2422,0.3829,0.3303,-17.4%,64.0%,50.3%,44.7%,62.8%,39.4%,61.9%,52.3%,36.2%,41.7%,30.0%,42.9%,46.9%,44.2%,62.3%,61.2%,64.8%,Liberalism,False,0,0,Gemma4UnifiedForConditionalGeneration,30.8,0.67,11.7,6.0,0.345,8.0,52.0,0.828,0.441,0.349,1.327,0.428,0.302,76.6,6993.0,124.3,21.62,4.0,4.3
1250
- google/gemma-4-12B-it (<|channel>thought prefill),https://huggingface.co/google/gemma-4-12B-it,6/3/2026,6/9/2026,gemma-4 w/ <|channel>thought prefill,12.0,12.0,12.0,False,False,True,36.32,18.59,16.64,1.8,1.8,1.5,2.2,3.0,1.5,29.47,41.67,24.48,22.25,16.64,0.1765,0.1072,0.2159,0.3944,0.2186,-15.7%,65.1%,48.1%,42.8%,60.4%,44.6%,61.7%,50.6%,34.6%,41.0%,29.0%,45.2%,47.3%,36.0%,56.2%,56.2%,68.8%,Liberalism,True,5630,7,Gemma4UnifiedForConditionalGeneration,29.5,0.68,11.9,6.3,0.331,8.0,68.0,0.832,0.426,0.34,1.527,0.276,0.186,64.8,10270.0,130.7,21.5,3.3,4.2
 
 
 
 
 
 
1246
  "anthropic/claude-opus-4-8 (adaptive, effort=high)","https://huggingface.co/anthropic/claude-opus-4-8 (adaptive, effort=high)",5/28/2026,5/29/2026,,,,,FALSE,FALSE,TRUE,64.33,55.83,75.0,9.4,7.6,5.9,1.8,2.0,1.5,60.4,80.76,37.59,62.85,75.0,0.7395,0.4656,0.6979,0.7692,0.4701,-15.6%,62.4%,44.7%,46.8%,55.6%,47.7%,63.1%,44.8%,36.2%,40.8%,35.6%,49.6%,52.3%,38.5%,47.7%,58.1%,60.8%,Liberalism,True,0,0,,51.6,0.98,12.1,4.3,0.379,9.0,58.0,0.842,0.432,0.324,1.14,0.58,0.422,17.8,2741.0,64.3,17.93,1.5,1.4
1247
  "anthropic/claude-opus-4-8 (adaptive, effort=xhigh)","https://huggingface.co/anthropic/claude-opus-4-8 (adaptive, effort=xhigh)",5/28/2026,5/29/2026,,,,,FALSE,FALSE,TRUE,65.64,56.51,76.01,9.4,6.5,7.5,1.8,2.0,1.5,63.7,83.05,46.9,61.15,76.01,0.6047,0.6063,0.6442,0.7305,0.4719,-14.4%,61.2%,44.9%,46.0%,56.4%,47.1%,61.7%,43.5%,39.0%,40.0%,37.3%,47.5%,52.1%,38.5%,50.4%,59.2%,59.6%,Liberalism,True,0,0,,50.5,0.94,11.8,4.4,0.385,6.0,54.0,0.85,0.433,0.326,1.117,0.635,0.405,24.3,1874.0,69.7,18.35,1.8,2.1
1248
  "anthropic/claude-opus-4-8 (adaptive, effort=max)","https://huggingface.co/anthropic/claude-opus-4-8 (adaptive, effort=max)",5/28/2026,5/29/2026,,,,,FALSE,FALSE,TRUE,65.88,52.64,67.71,8.8,6.5,5.4,2.2,3.0,1.5,65.39,81.18,49.66,65.35,67.71,0.6696,0.6475,0.6952,0.7526,0.5025,-18.3%,61.7%,47.2%,47.8%,59.0%,45.0%,57.7%,44.4%,38.8%,39.0%,37.3%,49.8%,56.5%,37.1%,52.7%,61.7%,62.7%,Liberalism,True,0,0,,49.6,0.95,11.8,4.3,0.403,9.0,76.0,0.843,0.432,0.348,1.087,0.618,0.434,21.1,1667.0,64.6,18.12,0.9,2.7
1249
+ google/gemma-4-12B-it,https://huggingface.co/google/gemma-4-12B-it,6/3/2026,6/9/2026,gemma-4,12.0,12.0,12.0,FALSE,FALSE,TRUE,31.6,15.2,16.56,2.9,1.1,1.3,1.2,1.0,1.5,25.81,35.93,16.21,25.29,16.56,0.1331,0.1761,0.2422,0.3829,0.3303,-17.4%,64.0%,50.3%,44.7%,62.8%,39.4%,61.9%,52.3%,36.2%,41.7%,30.0%,42.9%,46.9%,44.2%,62.3%,61.2%,64.8%,Liberalism,False,0,0,Gemma4UnifiedForConditionalGeneration,30.8,0.67,11.7,6.0,0.345,8.0,52.0,0.828,0.441,0.349,1.327,0.428,0.302,76.6,6993.0,124.3,21.62,4.0,4.3
1250
+ google/gemma-4-12B-it (<|channel>thought prefill),https://huggingface.co/google/gemma-4-12B-it,6/3/2026,6/9/2026,gemma-4 w/ <|channel>thought prefill,12.0,12.0,12.0,FALSE,FALSE,TRUE,36.32,18.59,16.64,1.8,1.8,1.5,2.2,3.0,1.5,29.47,41.67,24.48,22.25,16.64,0.1765,0.1072,0.2159,0.3944,0.2186,-15.7%,65.1%,48.1%,42.8%,60.4%,44.6%,61.7%,50.6%,34.6%,41.0%,29.0%,45.2%,47.3%,36.0%,56.2%,56.2%,68.8%,Liberalism,True,5630,7,Gemma4UnifiedForConditionalGeneration,29.5,0.68,11.9,6.3,0.331,8.0,68.0,0.832,0.426,0.34,1.527,0.276,0.186,64.8,10270.0,130.7,21.5,3.3,4.2
1251
+ "anthropic/claude-fable-5 (adaptive, effort=low)","https://huggingface.co/anthropic/claude-fable-5 (adaptive, effort=low)",6/9/2026,6/10/2026,,,,,FALSE,FALSE,TRUE,71.93,45.87,62.56,4.1,6.8,7.3,1.2,1.0,1.5,67.52,81.3,56.55,64.69,62.56,0.519,0.8409,0.6373,0.724,0.5133,-21.4%,66.1%,45.3%,47.8%,59.3%,45.2%,62.7%,43.8%,33.1%,35.4%,33.1%,52.3%,54.4%,36.9%,53.5%,61.9%,62.5%,Liberalism,True,0,0,,52.7,0.83,11.8,4.6,0.388,2.0,60.0,0.858,0.414,0.341,1.09,0.497,0.447,28.9,824.0,70.4,18.42,1.3,1.2
1252
+ "anthropic/claude-fable-5 (adaptive, effort=medium)","https://huggingface.co/anthropic/claude-fable-5 (adaptive, effort=medium)",6/9/2026,6/10/2026,,,,,FALSE,FALSE,TRUE,72.59,52.75,70.37,7.1,7.3,6.7,1.8,2.0,1.5,71.17,85.7,64.83,62.98,70.37,0.5182,0.8355,0.6027,0.7257,0.467,-21.4%,65.4%,45.5%,47.6%,59.5%,45.2%,62.9%,44.6%,36.9%,34.6%,32.3%,49.8%,54.8%,38.1%,54.2%,62.1%,62.3%,Liberalism,True,0,0,,53.3,0.83,11.2,4.5,0.382,2.0,64.0,0.857,0.41,0.331,1.13,0.473,0.391,28.9,846.0,74.0,18.4,1.1,1.4
1253
+ "anthropic/claude-fable-5 (adaptive, effort=high)","https://huggingface.co/anthropic/claude-fable-5 (adaptive, effort=high)",6/9/2026,6/10/2026,,,,,FALSE,FALSE,TRUE,74.23,55.92,77.63,7.1,7.3,8.9,1.2,1.0,1.5,73.02,84.38,64.83,69.85,77.63,0.8359,0.8945,0.5991,0.6716,0.4916,-22.0%,66.1%,45.1%,48.7%,59.4%,45.2%,63.8%,44.2%,34.4%,34.6%,32.7%,54.4%,54.6%,37.1%,51.9%,61.2%,65.2%,Liberalism,True,0,0,,51.9,0.85,11.4,4.9,0.398,2.0,74.0,0.864,0.414,0.341,1.113,0.464,0.423,13.3,601.0,74.3,18.93,1.1,1.8
1254
+ "anthropic/claude-fable-5 (adaptive, effort=xhigh)","https://huggingface.co/anthropic/claude-fable-5 (adaptive, effort=xhigh)",6/9/2026,6/10/2026,,,,,FALSE,FALSE,TRUE,71.71,52.0,71.75,4.1,7.7,9.0,1.2,1.0,1.5,70.88,81.95,59.31,71.38,71.75,0.7479,0.9685,0.7065,0.6575,0.4884,-23.1%,66.6%,45.9%,49.6%,60.7%,43.5%,63.3%,44.6%,32.1%,35.4%,32.7%,54.0%,53.5%,41.2%,54.6%,63.5%,64.0%,Liberalism,True,0,0,,53.0,0.84,11.1,4.7,0.406,2.0,80.0,0.866,0.415,0.348,1.12,0.442,0.421,17.4,255.0,63.4,19.07,1.3,1.1
1255
+ "anthropic/claude-fable-5 (adaptive, effort=max)","https://huggingface.co/anthropic/claude-fable-5 (adaptive, effort=max)",6/9/2026,6/10/2026,,,,,FALSE,FALSE,TRUE,73.66,44.66,60.74,2.9,6.2,8.5,1.2,1.0,1.5,76.72,84.62,73.1,72.43,60.74,0.7781,0.9607,0.696,0.6768,0.5099,-17.4%,65.1%,44.7%,47.1%,58.1%,43.8%,65.0%,42.9%,35.2%,34.8%,34.8%,51.7%,51.7%,37.9%,53.1%,59.2%,62.1%,Liberalism,True,0,0,,46.5,0.83,11.0,4.4,0.376,2.0,64.0,0.862,0.414,0.336,1.097,0.438,0.439,16.0,297.0,64.5,18.88,1.1,2.1