Upload ugi-leaderboard-data.csv

ugi-leaderboard-data.csv

@@ -1,4 +1,4 @@
-author/model_name,Model Link,Release Date,Test Date,Prompt Template,Active Parameters,Total Parameters,#P,Is Finetuned,Is Merged,Is Foundation,Writing ✍️,UGI 🏆,Hazardous,Entertainment,SocPol,W/10 👍,W/10-Direct,W/10-Adherence,NatInt 💡,Standard,Pop Culture,World Model,UGI non-W/10,wm_recipe_percent_error_score,wm_geoguessr_mae_score,wm_weight_percent_error_score,wm_music_mae_score,wm_youtube_view_percent_error_score,Show Rec Score,Political Lean 📋,dipl,govt,econ,scty,Federal-Unitary,Democratic-Autocratic,Security-Freedom,Nationalism-Internationalism,Militarist-Pacifist,Assimilationist-Multiculturalist,Collectivize-Privatize,Planned-LaissezFaire,Isolationism-Globalism,Irreligious-Religious,Progressive-Traditional,Acceleration-Bioconservative,12axes Ideology,Is Thinking Model,Avg Thinking Chars,Repetition Interrupts,Architecture,Dialogue_Percentage,Verb_to_Noun_Ratio,Adjective_Adverb_Percentage,Readability_Grade_Level,avg_writing_style_score,avg_length_error_pct,creative_writing_wc_exceeded_pct,originality_score,internal_semantic_redundancy,lexical_stuckness,Show Rec MAE,Show Rec Std Dev Error,Show Rec Pearson,wm_recipe_percent_error,wm_geoguesser_mae,wm_weight_percent_error,wm_music_mae,wm_youtube_view_percent_error,avg_nsfw_score,avg_dark_score
+author/model_name,Model Link,Release Date,Test Date,Prompt Template,Active Parameters,Total Parameters,#P,Is Finetuned,Is Merged,Is Foundation,Writing ✍️,UGI 🏆,Hazardous,Entertainment,SocPol,W/10 👍,W/10-Direct,W/10-Adherence,NatInt 💡,Standard,Pop Culture,World Model,UGI non-W/10,wm_recipe_percent_error_score,wm_geoguessr_mae_score,wm_weight_percent_error_score,wm_music_mae_score,wm_youtube_view_percent_error_score,Show Rec Score,Political Lean 📋,dipl,govt,econ,scty,Federal-Unitary,Democratic-Autocratic,Security-Freedom,Nationalism-Internationalism,Militarist-Pacifist,Assimilationist-Multiculturalist,Collectivize-Privatize,Planned-LaissezFaire,Isolationism-Globalism,Irreligious-Religious,Progressive-Traditional,Acceleration-Bioconservative,12axes Ideology,Is Thinking Model,Avg Thinking Chars,Repetition Interrupts,Architecture,Dialogue_Percentage,Verb_to_Noun_Ratio,Adjective_Adverb_Percentage,Readability_Grade_Level,avg_writing_style_score,avg_length_error_pct,creative_writing_wc_exceeded_pct,originality_score,internal_semantic_redundancy,lexical_stuckness,Show Rec MAE,Show Rec Std Dev Error,Show Rec Correlation,wm_recipe_percent_error,wm_geoguesser_mae,wm_weight_percent_error,wm_music_mae,wm_youtube_view_percent_error,avg_nsfw_score,avg_dark_score
 mistralai/Mistral-Small-3.1-24B-Instruct-2503,https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503,3/17/2025,9/6/2025,mistral V7-Tekken,24.0,24.0,24.0,FALSE,FALSE,TRUE,32.08,37.5,2.4,2.2,4.2,6.5,5.0,8.0,27.12,33.39,24.48,23.49,28.91,0.1739,0.2315,0.1547,0.3556,0.2378,0.2561,-13.9%,61.4%,43.1%,43.7%,57.7%,45.2%,67.7%,42.1%,41.0%,37.3%,37.5%,47.9%,50.4%,32.7%,51.5%,60.4%,61.2%,Liberalism,False,0,0,Mistral3ForConditionalGeneration,48.5,0.93,12.1,5.5,0.353,11.0,38.0,0.894,0.524,0.306,1.49,0.217,0.229,65.4,5564.0,149.7,21.9,194.3,2.7,1.5
 mistralai/Mistral-Small-24B-Instruct-2501,https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501,1/30/2025,9/6/2025,mistral V7-Tekken,24.0,24.0,24.0,FALSE,FALSE,TRUE,33.94,35.3,1.8,2.5,3.4,6.5,5.0,8.0,25.88,32.9,19.66,25.09,26.02,0.3238,0.1717,0.1817,0.2595,0.2523,0.3162,-16.8%,65.2%,47.6%,43.3%,60.1%,39.2%,65.0%,47.1%,36.0%,33.5%,34.8%,49.0%,51.2%,29.8%,57.7%,61.0%,61.7%,Liberalism,False,0,0,MistralForCausalLM,44.8,0.9,12.6,5.6,0.349,8.0,42.0,0.88,0.511,0.297,1.343,0.306,0.265,43.4,7137.0,140.4,23.03,191.8,1.7,1.0
 mistralai/Mistral-Small-3.2-24B-Instruct-2506,https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506,6/20/2025,9/6/2025,mistral V7-Tekken,24.0,24.0,24.0,FALSE,FALSE,TRUE,36.97,36.92,3.5,2.1,3.2,6.5,5.0,8.0,24.92,31.15,17.24,26.36,28.15,0.2936,0.2262,0.1863,0.2354,0.4117,0.2282,-14.0%,59.7%,43.7%,41.7%,62.8%,47.5%,65.6%,44.2%,39.6%,41.2%,40.0%,52.1%,40.4%,32.7%,64.2%,59.0%,65.4%,Liberalism,False,0,0,Mistral3ForConditionalGeneration,35.9,0.92,13.1,5.1,0.348,17.0,51.0,0.892,0.475,0.283,1.52,0.243,0.194,46.5,5675.0,139.0,23.37,169.8,4.4,5.0