DontPlanToEnd commited on
Commit
d698d03
·
verified ·
1 Parent(s): 6c438d0

Upload ugi-leaderboard-data.csv

Browse files
Files changed (1) hide show
  1. ugi-leaderboard-data.csv +10 -10
ugi-leaderboard-data.csv CHANGED
@@ -1066,7 +1066,7 @@ openai/gpt-5.4-2026-03-05 (reasoning_effort=low),https://huggingface.co/openai/g
1066
  openai/gpt-5.4-2026-03-05 (reasoning_effort=medium),https://huggingface.co/openai/gpt-5.4-2026-03-05 (reasoning_effort=medium),3/5/2026,3/5/2026,,,,,FALSE,FALSE,TRUE,67.34,33.8,39.45,0.0,4.3,6.7,2.2,3.0,1.5,68.36,80.22,67.93,56.93,39.45,0.6941,0.5202,0.6737,0.535,0.4236,-28.5%,70.6%,47.6%,44.8%,65.6%,40.8%,61.9%,45.4%,28.8%,35.4%,24.0%,51.2%,51.2%,31.9%,66.2%,65.4%,65.2%,Liberalism,True,0,0,,29.1,0.83,13.5,4.9,0.394,53.0,98.0,0.847,0.43,0.311,1.233,0.289,0.381,19.9,2369.0,66.7,20.18,1.7,4.6
1067
  openai/gpt-5.4-2026-03-05 (reasoning_effort=high),https://huggingface.co/openai/gpt-5.4-2026-03-05 (reasoning_effort=high),3/5/2026,3/5/2026,,,,,FALSE,FALSE,TRUE,68.82,38.96,49.69,0.0,5.6,8.2,1.8,2.0,1.5,71.25,85.6,64.48,63.67,49.69,0.6725,0.8421,0.7386,0.511,0.4191,-29.2%,70.1%,46.6%,49.9%,64.2%,42.5%,62.5%,44.8%,26.0%,37.7%,26.0%,59.0%,58.1%,32.7%,64.0%,61.2%,67.5%,Liberalism,True,0,0,,29.0,0.84,13.1,4.7,0.4,46.0,94.0,0.845,0.424,0.31,1.227,0.357,0.378,20.9,819.0,60.1,20.4,1.5,4.7
1068
  openai/gpt-5.4-2026-03-05 (reasoning_effort=xhigh),https://huggingface.co/openai/gpt-5.4-2026-03-05 (reasoning_effort=xhigh),3/5/2026,3/5/2026,,,,,FALSE,FALSE,TRUE,68.65,41.71,56.32,2.4,5.4,8.6,1.2,1.0,1.5,73.53,83.54,70.69,66.34,56.32,0.7984,0.8882,0.6878,0.5018,0.441,-26.9%,70.1%,45.1%,47.5%,63.4%,42.9%,63.3%,41.7%,25.0%,36.9%,27.7%,58.3%,54.2%,30.0%,61.9%,61.9%,66.5%,Liberalism,True,0,0,,30.8,0.89,12.2,4.2,0.398,30.0,72.0,0.856,0.425,0.318,1.183,0.451,0.393,15.1,628.0,65.3,20.48,2.2,4.1
1069
- xai/grok-4.20-multi-agent-beta-0309 (agent_count=4),https://huggingface.co/xai/grok-4.20-multi-agent-beta-0309 (agent_count=4),3/11/2026,3/13/2026,,,,,FALSE,FALSE,TRUE,63.13,70.0,72.51,8.8,4.9,8.8,6.5,7.0,6.0,56.34,76.88,49.66,42.5,72.51,0.4634,0.1924,0.5306,0.5498,0.3888,12.7%,58.5%,45.3%,24.0%,66.6%,41.7%,60.4%,38.1%,44.0%,36.9%,43.8%,19.2%,27.7%,25.2%,74.6%,51.2%,74.0%,Classical Liberalism,True,47312,0,,35.6,0.68,13.3,5.7,0.356,38.0,96.0,0.885,0.432,0.276,1.237,0.402,0.332,32.3,6506.0,81.6,20.05,9.7,5.0
1070
  xai/grok-4.20-beta-0309-reasoning,https://huggingface.co/xai/grok-4.20-beta-0309-reasoning,3/10/2026,3/13/2026,,,,,FALSE,FALSE,TRUE,57.41,53.16,52.25,6.5,4.0,5.7,5.5,5.0,6.0,53.67,75.82,41.38,43.82,52.25,0.4124,0.4036,0.5568,0.3829,0.4353,29.7%,49.8%,42.6%,17.5%,62.6%,56.5%,52.7%,37.1%,57.9%,43.3%,49.4%,11.2%,16.9%,24.4%,67.5%,40.8%,79.4%,Classical Liberalism,True,0,0,,25.3,0.74,13.4,5.6,0.33,43.0,96.0,0.877,0.438,0.299,1.217,0.342,0.399,35.8,3244.0,78.8,21.62,9.5,5.9
1071
  xai/grok-4.20-beta-0309-non-reasoning,https://huggingface.co/xai/grok-4.20-beta-0309-non-reasoning,3/10/2026,3/13/2026,,,,,FALSE,FALSE,TRUE,43.88,30.25,25.37,2.4,2.3,2.9,4.0,5.0,3.0,39.77,55.31,33.45,30.56,25.37,0.2202,0.2511,0.3307,0.378,0.3481,11.7%,53.3%,46.3%,30.0%,57.6%,38.3%,58.1%,35.4%,54.0%,41.5%,44.6%,24.8%,31.5%,33.8%,54.4%,49.0%,69.4%,Classical Liberalism,False,0,0,,23.2,0.76,14.0,4.6,0.353,37.0,88.0,0.849,0.439,0.303,1.297,0.373,0.302,56.5,5180.0,107.5,21.67,8.8,6.8
1072
  Qwen/Qwen3.5-35B-A3B (no thinking),https://huggingface.co/Qwen/Qwen3.5-35B-A3B,2/24/2026,3/14/2026,chatml w/ no thinking,3.0,35.0,35.0,FALSE,FALSE,TRUE,37.0,23.15,20.98,4.1,0.8,2.1,2.8,4.0,1.5,24.97,24.78,12.41,37.7,20.98,0.4402,0.1294,0.4529,0.6033,0.2591,-20.7%,65.2%,46.5%,44.4%,56.8%,42.3%,66.2%,48.1%,37.3%,38.3%,28.8%,45.4%,50.8%,36.9%,46.5%,61.7%,62.3%,Liberalism,False,0,3,Qwen3_5MoeForConditionalGeneration,40.6,0.76,12.7,6.3,0.329,17.0,89.0,0.823,0.439,0.32,1.513,0.112,0.22,33.8,8908.0,90.5,19.57,3.0,5.0
@@ -1184,12 +1184,12 @@ moonshotai/Kimi-K2.6 (reasoning=disabled),https://huggingface.co/moonshotai/Kimi
1184
  moonshotai/Kimi-K2.6 (reasoning=enabled),https://huggingface.co/moonshotai/Kimi-K2.6,4/20/2026,4/20/2026,,32.0,1000.0,1000.0,FALSE,FALSE,TRUE,64.4,51.08,67.87,8.2,6.7,5.7,1.8,2.0,1.5,65.25,71.92,74.14,49.71,67.87,0.3443,0.7346,0.6846,0.3371,0.3847,-27.6%,69.2%,45.3%,45.8%,60.4%,45.2%,61.5%,42.7%,32.3%,33.5%,26.7%,52.7%,54.4%,30.2%,54.2%,64.6%,62.5%,Liberalism,True,0,0,,30.1,0.73,11.5,5.4,0.347,18.0,78.0,0.881,0.406,0.305,1.263,0.309,0.334,41.4,1268.0,65.6,22.1,1.7,4.0
1185
  llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic,https://huggingface.co/llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic,4/7/2026,4/20/2026,gemma-4,4.0,26.0,26.0,TRUE,FALSE,FALSE,42.12,44.96,23.69,1.2,3.1,2.5,8.8,8.0,9.5,33.71,42.42,23.45,35.27,23.69,0.1922,0.2031,0.4965,0.4442,0.4274,-14.9%,60.8%,47.3%,48.5%,54.1%,44.2%,62.5%,48.5%,36.2%,50.6%,30.6%,51.0%,47.5%,46.9%,40.4%,53.8%,68.1%,Liberalism,False,0,0,Gemma4ForConditionalGeneration,31.5,0.66,12.8,6.8,0.34,10.0,76.0,0.825,0.436,0.346,1.197,0.378,0.367,61.5,6220.0,85.4,21.02,4.0,3.1
1186
  llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic (<|channel>thought prefill),https://huggingface.co/llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic,4/7/2026,4/20/2026,gemma-4 w/ <|channel>thought prefill,4.0,26.0,26.0,TRUE,FALSE,FALSE,45.88,52.39,28.58,3.5,3.1,2.1,10.0,10.0,10.0,35.71,45.33,28.62,33.19,28.58,0.2109,0.1797,0.5963,0.3192,0.3536,-15.6%,62.3%,50.6%,44.7%,57.9%,40.0%,63.5%,55.2%,34.0%,47.3%,31.9%,49.0%,44.6%,40.6%,42.3%,58.5%,72.9%,Liberalism,True,5940,7,Gemma4ForConditionalGeneration,29.3,0.68,13.1,6.9,0.342,11.0,76.0,0.829,0.427,0.341,1.27,0.436,0.298,58.0,6879.0,74.6,22.3,3.5,3.3
1187
- Qwen/Qwen3.6-35B-A3B (no think),https://huggingface.co/Qwen/Qwen3.6-35B-A3B,4/15/2026,4/22/2026,chatml w/ no think,3.0,35.0,35.0,False,False,True,35.83,16.02,14.03,0.0,1.4,2.6,2.0,4.0,0.0,25.43,37.6,7.93,30.75,14.03,0.2938,0.1107,0.3101,0.6015,0.2212,-19.6%,66.9%,46.5%,42.9%,56.5%,44.2%,63.3%,46.9%,34.2%,37.1%,28.1%,45.4%,49.2%,34.2%,46.5%,60.2%,62.9%,Liberalism,False,0,0,Qwen3_5MoeForConditionalGeneration,23.2,0.75,12.8,5.7,0.318,10.0,70.0,0.84,0.432,0.327,1.67,0.056,0.196,46.5,10024.0,111.0,19.58,2.6,3.6
1188
- Qwen/Qwen3.6-35B-A3B (<think> prefill),https://huggingface.co/Qwen/Qwen3.6-35B-A3B,4/15/2026,4/25/2026,chatml w/ <think> prefill,3.0,35.0,35.0,False,False,True,45.36,21.51,21.01,2.9,1.2,2.6,2.2,3.0,1.5,31.03,49.93,15.17,27.98,21.01,0.2653,0.1671,0.5085,0.2297,0.2284,-19.4%,67.9%,45.8%,43.4%,60.1%,47.3%,60.4%,45.0%,35.0%,31.5%,29.8%,45.8%,51.0%,33.3%,53.3%,60.4%,66.5%,Liberalism,True,11175,10,Qwen3_5MoeForConditionalGeneration,20.2,0.76,14.2,6.4,0.277,16.0,30.0,0.853,0.38,0.244,1.617,0.14,0.216,49.9,7295.0,84.0,23.45,2.0,2.3
1189
- openai/gpt-5.5-2026-04-23 (reasoning_effort=none),https://huggingface.co/openai/gpt-5.5-2026-04-23 (reasoning_effort=none),4/23/2026,4/25/2026,,,,,False,False,True,51.47,49.97,63.7,6.5,5.6,7.2,2.2,3.0,1.5,62.57,71.92,64.14,51.64,63.7,0.2371,0.4253,0.7105,0.7337,0.4754,-27.6%,73.0%,44.4%,49.6%,61.0%,42.1%,66.9%,42.1%,25.6%,30.4%,25.0%,54.8%,56.5%,37.5%,56.7%,60.8%,65.4%,Liberalism,False,0,0,,27.6,0.86,12.2,4.3,0.397,98.0,100.0,0.839,0.431,0.339,1.117,0.58,0.407,53.8,3055.0,63.0,18.32,1.5,4.1
1190
- openai/gpt-5.5-2026-04-23 (reasoning_effort=low),https://huggingface.co/openai/gpt-5.5-2026-04-23 (reasoning_effort=low),4/23/2026,4/25/2026,,,,,False,False,True,58.69,44.98,52.48,2.4,5.3,7.6,3.0,3.0,3.0,71.39,84.94,62.76,66.46,52.48,0.6866,0.623,0.7826,0.7751,0.4556,-25.4%,69.7%,44.9%,48.8%,61.7%,42.5%,66.9%,44.2%,27.1%,32.5%,31.2%,55.0%,54.6%,36.7%,56.5%,64.6%,64.0%,Liberalism,False,0,0,,27.6,0.88,12.2,4.2,0.406,96.0,100.0,0.843,0.428,0.33,1.167,0.472,0.408,20.3,1789.0,55.5,17.87,2.0,3.9
1191
- openai/gpt-5.5-2026-04-23 (reasoning_effort=medium),https://huggingface.co/openai/gpt-5.5-2026-04-23 (reasoning_effort=medium),4/23/2026,4/25/2026,,,,,False,False,True,64.75,49.19,62.54,4.1,5.6,8.7,2.2,3.0,1.5,77.12,85.58,74.14,71.64,62.54,0.8053,0.8712,0.7425,0.7321,0.4308,-31.6%,73.0%,46.0%,49.5%,62.4%,42.3%,65.8%,46.2%,25.8%,31.7%,23.5%,55.4%,54.4%,38.8%,55.4%,66.0%,65.8%,Liberalism,False,0,0,,28.4,0.87,12.0,4.2,0.409,71.0,100.0,0.854,0.43,0.332,1.193,0.46,0.383,14.8,699.0,59.7,18.33,2.4,4.4
1192
- openai/gpt-5.5-2026-04-23 (reasoning_effort=high),https://huggingface.co/openai/gpt-5.5-2026-04-23 (reasoning_effort=high),4/23/2026,4/25/2026,,,,,False,False,True,67.91,50.98,67.71,6.5,5.8,8.3,1.8,2.0,1.5,79.27,82.26,81.38,74.16,67.71,0.865,0.9579,0.7839,0.6838,0.4176,-31.7%,72.3%,45.3%,47.2%,64.1%,44.0%,63.5%,43.5%,26.7%,32.5%,24.0%,56.0%,55.0%,30.6%,58.3%,66.0%,67.9%,Liberalism,False,0,0,,28.3,0.86,11.5,4.1,0.412,42.0,88.0,0.863,0.427,0.325,1.21,0.49,0.378,11.8,312.0,55.3,18.82,1.1,3.1
1193
- openai/gpt-5.5-2026-04-23 (reasoning_effort=xhigh),https://huggingface.co/openai/gpt-5.5-2026-04-23 (reasoning_effort=xhigh),4/23/2026,4/25/2026,,,,,False,False,True,69.66,51.19,65.53,5.9,5.6,8.2,2.2,3.0,1.5,78.16,88.3,76.9,69.29,65.53,0.8434,0.8631,0.7278,0.6361,0.3939,-32.1%,72.8%,44.9%,48.0%,63.9%,45.2%,63.5%,43.3%,27.5%,30.6%,23.5%,56.5%,56.9%,30.6%,57.7%,65.0%,69.0%,Liberalism,False,0,0,,30.3,0.84,11.0,4.1,0.403,13.0,58.0,0.887,0.426,0.307,1.243,0.437,0.356,12.9,733.0,61.2,19.27,0.9,4.3
1194
- xai/grok-4.20-0309-non-reasoning,https://huggingface.co/xai/grok-4.20-0309-non-reasoning,3/19/2026,4/25/2026,,,,,False,False,True,47.15,51.77,46.4,8.8,3.1,3.1,6.2,6.0,6.5,40.76,52.25,36.21,33.82,46.4,0.3499,0.2187,0.3252,0.4425,0.3545,11.8%,55.4%,46.5%,28.7%,60.6%,40.0%,56.2%,35.8%,52.7%,38.3%,42.7%,32.9%,20.8%,32.3%,62.3%,48.1%,71.5%,Classical Liberalism,False,0,0,,22.4,0.77,13.8,4.8,0.343,36.0,100.0,0.851,0.425,0.294,1.287,0.394,0.31,40.9,5843.0,108.4,21.03,8.5,8.2
1195
- xai/grok-4.20-0309-reasoning,https://huggingface.co/xai/grok-4.20-0309-reasoning,3/19/2026,4/25/2026,,,,,False,False,True,55.26,64.23,58.84,7.1,4.5,6.7,7.5,7.0,8.0,52.75,70.23,46.9,41.13,58.84,0.3714,0.3311,0.5281,0.4425,0.3835,27.9%,49.8%,43.6%,18.6%,62.2%,49.2%,56.2%,36.2%,57.1%,45.0%,48.5%,13.1%,18.5%,24.2%,66.5%,40.8%,79.4%,Classical Liberalism,False,0,0,,22.9,0.73,13.2,5.3,0.325,46.0,100.0,0.865,0.43,0.29,1.267,0.385,0.349,39.0,3995.0,81.9,21.03,9.9,6.2
 
1066
  openai/gpt-5.4-2026-03-05 (reasoning_effort=medium),https://huggingface.co/openai/gpt-5.4-2026-03-05 (reasoning_effort=medium),3/5/2026,3/5/2026,,,,,FALSE,FALSE,TRUE,67.34,33.8,39.45,0.0,4.3,6.7,2.2,3.0,1.5,68.36,80.22,67.93,56.93,39.45,0.6941,0.5202,0.6737,0.535,0.4236,-28.5%,70.6%,47.6%,44.8%,65.6%,40.8%,61.9%,45.4%,28.8%,35.4%,24.0%,51.2%,51.2%,31.9%,66.2%,65.4%,65.2%,Liberalism,True,0,0,,29.1,0.83,13.5,4.9,0.394,53.0,98.0,0.847,0.43,0.311,1.233,0.289,0.381,19.9,2369.0,66.7,20.18,1.7,4.6
1067
  openai/gpt-5.4-2026-03-05 (reasoning_effort=high),https://huggingface.co/openai/gpt-5.4-2026-03-05 (reasoning_effort=high),3/5/2026,3/5/2026,,,,,FALSE,FALSE,TRUE,68.82,38.96,49.69,0.0,5.6,8.2,1.8,2.0,1.5,71.25,85.6,64.48,63.67,49.69,0.6725,0.8421,0.7386,0.511,0.4191,-29.2%,70.1%,46.6%,49.9%,64.2%,42.5%,62.5%,44.8%,26.0%,37.7%,26.0%,59.0%,58.1%,32.7%,64.0%,61.2%,67.5%,Liberalism,True,0,0,,29.0,0.84,13.1,4.7,0.4,46.0,94.0,0.845,0.424,0.31,1.227,0.357,0.378,20.9,819.0,60.1,20.4,1.5,4.7
1068
  openai/gpt-5.4-2026-03-05 (reasoning_effort=xhigh),https://huggingface.co/openai/gpt-5.4-2026-03-05 (reasoning_effort=xhigh),3/5/2026,3/5/2026,,,,,FALSE,FALSE,TRUE,68.65,41.71,56.32,2.4,5.4,8.6,1.2,1.0,1.5,73.53,83.54,70.69,66.34,56.32,0.7984,0.8882,0.6878,0.5018,0.441,-26.9%,70.1%,45.1%,47.5%,63.4%,42.9%,63.3%,41.7%,25.0%,36.9%,27.7%,58.3%,54.2%,30.0%,61.9%,61.9%,66.5%,Liberalism,True,0,0,,30.8,0.89,12.2,4.2,0.398,30.0,72.0,0.856,0.425,0.318,1.183,0.451,0.393,15.1,628.0,65.3,20.48,2.2,4.1
1069
+ xai/grok-4.20-multi-agent-beta-0309 (agent_count=4),https://huggingface.co/xai/grok-4.20-multi-agent-beta-0309 (agent_count=4),3/10/2026,3/13/2026,,,,,FALSE,FALSE,TRUE,63.13,70.0,72.51,8.8,4.9,8.8,6.5,7.0,6.0,56.34,76.88,49.66,42.5,72.51,0.4634,0.1924,0.5306,0.5498,0.3888,12.7%,58.5%,45.3%,24.0%,66.6%,41.7%,60.4%,38.1%,44.0%,36.9%,43.8%,19.2%,27.7%,25.2%,74.6%,51.2%,74.0%,Classical Liberalism,True,47312,0,,35.6,0.68,13.3,5.7,0.356,38.0,96.0,0.885,0.432,0.276,1.237,0.402,0.332,32.3,6506.0,81.6,20.05,9.7,5.0
1070
  xai/grok-4.20-beta-0309-reasoning,https://huggingface.co/xai/grok-4.20-beta-0309-reasoning,3/10/2026,3/13/2026,,,,,FALSE,FALSE,TRUE,57.41,53.16,52.25,6.5,4.0,5.7,5.5,5.0,6.0,53.67,75.82,41.38,43.82,52.25,0.4124,0.4036,0.5568,0.3829,0.4353,29.7%,49.8%,42.6%,17.5%,62.6%,56.5%,52.7%,37.1%,57.9%,43.3%,49.4%,11.2%,16.9%,24.4%,67.5%,40.8%,79.4%,Classical Liberalism,True,0,0,,25.3,0.74,13.4,5.6,0.33,43.0,96.0,0.877,0.438,0.299,1.217,0.342,0.399,35.8,3244.0,78.8,21.62,9.5,5.9
1071
  xai/grok-4.20-beta-0309-non-reasoning,https://huggingface.co/xai/grok-4.20-beta-0309-non-reasoning,3/10/2026,3/13/2026,,,,,FALSE,FALSE,TRUE,43.88,30.25,25.37,2.4,2.3,2.9,4.0,5.0,3.0,39.77,55.31,33.45,30.56,25.37,0.2202,0.2511,0.3307,0.378,0.3481,11.7%,53.3%,46.3%,30.0%,57.6%,38.3%,58.1%,35.4%,54.0%,41.5%,44.6%,24.8%,31.5%,33.8%,54.4%,49.0%,69.4%,Classical Liberalism,False,0,0,,23.2,0.76,14.0,4.6,0.353,37.0,88.0,0.849,0.439,0.303,1.297,0.373,0.302,56.5,5180.0,107.5,21.67,8.8,6.8
1072
  Qwen/Qwen3.5-35B-A3B (no thinking),https://huggingface.co/Qwen/Qwen3.5-35B-A3B,2/24/2026,3/14/2026,chatml w/ no thinking,3.0,35.0,35.0,FALSE,FALSE,TRUE,37.0,23.15,20.98,4.1,0.8,2.1,2.8,4.0,1.5,24.97,24.78,12.41,37.7,20.98,0.4402,0.1294,0.4529,0.6033,0.2591,-20.7%,65.2%,46.5%,44.4%,56.8%,42.3%,66.2%,48.1%,37.3%,38.3%,28.8%,45.4%,50.8%,36.9%,46.5%,61.7%,62.3%,Liberalism,False,0,3,Qwen3_5MoeForConditionalGeneration,40.6,0.76,12.7,6.3,0.329,17.0,89.0,0.823,0.439,0.32,1.513,0.112,0.22,33.8,8908.0,90.5,19.57,3.0,5.0
 
1184
  moonshotai/Kimi-K2.6 (reasoning=enabled),https://huggingface.co/moonshotai/Kimi-K2.6,4/20/2026,4/20/2026,,32.0,1000.0,1000.0,FALSE,FALSE,TRUE,64.4,51.08,67.87,8.2,6.7,5.7,1.8,2.0,1.5,65.25,71.92,74.14,49.71,67.87,0.3443,0.7346,0.6846,0.3371,0.3847,-27.6%,69.2%,45.3%,45.8%,60.4%,45.2%,61.5%,42.7%,32.3%,33.5%,26.7%,52.7%,54.4%,30.2%,54.2%,64.6%,62.5%,Liberalism,True,0,0,,30.1,0.73,11.5,5.4,0.347,18.0,78.0,0.881,0.406,0.305,1.263,0.309,0.334,41.4,1268.0,65.6,22.1,1.7,4.0
1185
  llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic,https://huggingface.co/llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic,4/7/2026,4/20/2026,gemma-4,4.0,26.0,26.0,TRUE,FALSE,FALSE,42.12,44.96,23.69,1.2,3.1,2.5,8.8,8.0,9.5,33.71,42.42,23.45,35.27,23.69,0.1922,0.2031,0.4965,0.4442,0.4274,-14.9%,60.8%,47.3%,48.5%,54.1%,44.2%,62.5%,48.5%,36.2%,50.6%,30.6%,51.0%,47.5%,46.9%,40.4%,53.8%,68.1%,Liberalism,False,0,0,Gemma4ForConditionalGeneration,31.5,0.66,12.8,6.8,0.34,10.0,76.0,0.825,0.436,0.346,1.197,0.378,0.367,61.5,6220.0,85.4,21.02,4.0,3.1
1186
  llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic (<|channel>thought prefill),https://huggingface.co/llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic,4/7/2026,4/20/2026,gemma-4 w/ <|channel>thought prefill,4.0,26.0,26.0,TRUE,FALSE,FALSE,45.88,52.39,28.58,3.5,3.1,2.1,10.0,10.0,10.0,35.71,45.33,28.62,33.19,28.58,0.2109,0.1797,0.5963,0.3192,0.3536,-15.6%,62.3%,50.6%,44.7%,57.9%,40.0%,63.5%,55.2%,34.0%,47.3%,31.9%,49.0%,44.6%,40.6%,42.3%,58.5%,72.9%,Liberalism,True,5940,7,Gemma4ForConditionalGeneration,29.3,0.68,13.1,6.9,0.342,11.0,76.0,0.829,0.427,0.341,1.27,0.436,0.298,58.0,6879.0,74.6,22.3,3.5,3.3
1187
+ Qwen/Qwen3.6-35B-A3B (no think),https://huggingface.co/Qwen/Qwen3.6-35B-A3B,4/15/2026,4/22/2026,chatml w/ no think,3.0,35.0,35.0,FALSE,FALSE,TRUE,35.83,16.02,14.03,0.0,1.4,2.6,2.0,4.0,0.0,25.43,37.6,7.93,30.75,14.03,0.2938,0.1107,0.3101,0.6015,0.2212,-19.6%,66.9%,46.5%,42.9%,56.5%,44.2%,63.3%,46.9%,34.2%,37.1%,28.1%,45.4%,49.2%,34.2%,46.5%,60.2%,62.9%,Liberalism,False,0,0,Qwen3_5MoeForConditionalGeneration,23.2,0.75,12.8,5.7,0.318,10.0,70.0,0.84,0.432,0.327,1.67,0.056,0.196,46.5,10024.0,111.0,19.58,2.6,3.6
1188
+ Qwen/Qwen3.6-35B-A3B (<think> prefill),https://huggingface.co/Qwen/Qwen3.6-35B-A3B,4/15/2026,4/25/2026,chatml w/ <think> prefill,3.0,35.0,35.0,FALSE,FALSE,TRUE,45.36,21.51,21.01,2.9,1.2,2.6,2.2,3.0,1.5,31.03,49.93,15.17,27.98,21.01,0.2653,0.1671,0.5085,0.2297,0.2284,-19.4%,67.9%,45.8%,43.4%,60.1%,47.3%,60.4%,45.0%,35.0%,31.5%,29.8%,45.8%,51.0%,33.3%,53.3%,60.4%,66.5%,Liberalism,True,11175,10,Qwen3_5MoeForConditionalGeneration,20.2,0.76,14.2,6.4,0.277,16.0,30.0,0.853,0.38,0.244,1.617,0.14,0.216,49.9,7295.0,84.0,23.45,2.0,2.3
1189
+ openai/gpt-5.5-2026-04-23 (reasoning_effort=none),https://huggingface.co/openai/gpt-5.5-2026-04-23 (reasoning_effort=none),4/23/2026,4/25/2026,,,,,FALSE,FALSE,TRUE,51.47,49.97,63.7,6.5,5.6,7.2,2.2,3.0,1.5,62.57,71.92,64.14,51.64,63.7,0.2371,0.4253,0.7105,0.7337,0.4754,-27.6%,73.0%,44.4%,49.6%,61.0%,42.1%,66.9%,42.1%,25.6%,30.4%,25.0%,54.8%,56.5%,37.5%,56.7%,60.8%,65.4%,Liberalism,False,0,0,,27.6,0.86,12.2,4.3,0.397,98.0,100.0,0.839,0.431,0.339,1.117,0.58,0.407,53.8,3055.0,63.0,18.32,1.5,4.1
1190
+ openai/gpt-5.5-2026-04-23 (reasoning_effort=low),https://huggingface.co/openai/gpt-5.5-2026-04-23 (reasoning_effort=low),4/23/2026,4/25/2026,,,,,FALSE,FALSE,TRUE,58.69,44.98,52.48,2.4,5.3,7.6,3.0,3.0,3.0,71.39,84.94,62.76,66.46,52.48,0.6866,0.623,0.7826,0.7751,0.4556,-25.4%,69.7%,44.9%,48.8%,61.7%,42.5%,66.9%,44.2%,27.1%,32.5%,31.2%,55.0%,54.6%,36.7%,56.5%,64.6%,64.0%,Liberalism,True,0,0,,27.6,0.88,12.2,4.2,0.406,96.0,100.0,0.843,0.428,0.33,1.167,0.472,0.408,20.3,1789.0,55.5,17.87,2.0,3.9
1191
+ openai/gpt-5.5-2026-04-23 (reasoning_effort=medium),https://huggingface.co/openai/gpt-5.5-2026-04-23 (reasoning_effort=medium),4/23/2026,4/25/2026,,,,,FALSE,FALSE,TRUE,64.75,49.19,62.54,4.1,5.6,8.7,2.2,3.0,1.5,77.12,85.58,74.14,71.64,62.54,0.8053,0.8712,0.7425,0.7321,0.4308,-31.6%,73.0%,46.0%,49.5%,62.4%,42.3%,65.8%,46.2%,25.8%,31.7%,23.5%,55.4%,54.4%,38.8%,55.4%,66.0%,65.8%,Liberalism,True,0,0,,28.4,0.87,12.0,4.2,0.409,71.0,100.0,0.854,0.43,0.332,1.193,0.46,0.383,14.8,699.0,59.7,18.33,2.4,4.4
1192
+ openai/gpt-5.5-2026-04-23 (reasoning_effort=high),https://huggingface.co/openai/gpt-5.5-2026-04-23 (reasoning_effort=high),4/23/2026,4/25/2026,,,,,FALSE,FALSE,TRUE,67.91,50.98,67.71,6.5,5.8,8.3,1.8,2.0,1.5,79.27,82.26,81.38,74.16,67.71,0.865,0.9579,0.7839,0.6838,0.4176,-31.7%,72.3%,45.3%,47.2%,64.1%,44.0%,63.5%,43.5%,26.7%,32.5%,24.0%,56.0%,55.0%,30.6%,58.3%,66.0%,67.9%,Liberalism,True,0,0,,28.3,0.86,11.5,4.1,0.412,42.0,88.0,0.863,0.427,0.325,1.21,0.49,0.378,11.8,312.0,55.3,18.82,1.1,3.1
1193
+ openai/gpt-5.5-2026-04-23 (reasoning_effort=xhigh),https://huggingface.co/openai/gpt-5.5-2026-04-23 (reasoning_effort=xhigh),4/23/2026,4/25/2026,,,,,FALSE,FALSE,TRUE,69.66,51.19,65.53,5.9,5.6,8.2,2.2,3.0,1.5,78.16,88.3,76.9,69.29,65.53,0.8434,0.8631,0.7278,0.6361,0.3939,-32.1%,72.8%,44.9%,48.0%,63.9%,45.2%,63.5%,43.3%,27.5%,30.6%,23.5%,56.5%,56.9%,30.6%,57.7%,65.0%,69.0%,Liberalism,True,0,0,,30.3,0.84,11.0,4.1,0.403,13.0,58.0,0.887,0.426,0.307,1.243,0.437,0.356,12.9,733.0,61.2,19.27,0.9,4.3
1194
+ xai/grok-4.20-0309-non-reasoning,https://huggingface.co/xai/grok-4.20-0309-non-reasoning,3/19/2026,4/25/2026,,,,,FALSE,FALSE,TRUE,47.15,51.77,46.4,8.8,3.1,3.1,6.2,6.0,6.5,40.76,52.25,36.21,33.82,46.4,0.3499,0.2187,0.3252,0.4425,0.3545,11.8%,55.4%,46.5%,28.7%,60.6%,40.0%,56.2%,35.8%,52.7%,38.3%,42.7%,32.9%,20.8%,32.3%,62.3%,48.1%,71.5%,Classical Liberalism,False,0,0,,22.4,0.77,13.8,4.8,0.343,36.0,100.0,0.851,0.425,0.294,1.287,0.394,0.31,40.9,5843.0,108.4,21.03,8.5,8.2
1195
+ xai/grok-4.20-0309-reasoning,https://huggingface.co/xai/grok-4.20-0309-reasoning,3/19/2026,4/25/2026,,,,,FALSE,FALSE,TRUE,55.26,64.23,58.84,7.1,4.5,6.7,7.5,7.0,8.0,52.75,70.23,46.9,41.13,58.84,0.3714,0.3311,0.5281,0.4425,0.3835,27.9%,49.8%,43.6%,18.6%,62.2%,49.2%,56.2%,36.2%,57.1%,45.0%,48.5%,13.1%,18.5%,24.2%,66.5%,40.8%,79.4%,Classical Liberalism,True,0,0,,22.9,0.73,13.2,5.3,0.325,46.0,100.0,0.865,0.43,0.29,1.267,0.385,0.349,39.0,3995.0,81.9,21.03,9.9,6.2