Upload ugi-leaderboard-data.csv

ugi-leaderboard-data.csv

@@ -578,7 +578,7 @@ arcee-ai/Homunculus (thinking=False),https://huggingface.co/arcee-ai/Homunculus,
 arcee-ai/Homunculus (thinking=True),https://huggingface.co/arcee-ai/Homunculus,6/2/2025,11/9/2025,chatml,12.0,12.0,12.0,TRUE,FALSE,FALSE,31.19,22.76,1.2,0.9,2.5,4.8,6.0,3.5,17.99,28.54,8.97,16.47,15.03,0.1295,0.1361,0.1044,0.2801,0.1735,-19.9%,66.8%,49.5%,46.7%,59.7%,49.0%,56.7%,54.2%,33.3%,34.8%,31.5%,48.1%,51.9%,40.2%,55.4%,61.2%,62.5%,Liberalism,True,2780,5,MistralForCausalLM,33.1,0.88,14.3,5.9,0.317,45.0,79.0,0.886,0.433,0.301,1.653,0.353,0.166,77.8,8569.0,174.0,22.77,2.7,4.5
 TheDrummer/Skyfall-36B-v2,https://huggingface.co/TheDrummer/Skyfall-36B-v2,2/3/2025,11/11/2025,mistral V7-Tekken,36.0,36.0,36.0,TRUE,FALSE,FALSE,38.8,30.17,2.9,2.1,1.4,6.0,7.0,5.0,26.65,26.5,24.14,29.3,20.85,0.291,0.1606,0.3188,0.446,0.2488,-18.9%,65.1%,45.6%,41.7%,61.0%,43.8%,66.5%,47.1%,39.2%,33.5%,31.9%,44.8%,46.9%,33.3%,60.4%,64.4%,58.3%,Liberalism,False,0,0,MistralForCausalLM,46.3,0.96,13.1,5.6,0.324,16.0,19.0,0.896,0.497,0.272,1.44,0.326,0.204,46.8,7530.0,109.5,21.0,9.1,7.5
 allura-org/Q3-30B-A3B-Designant,https://huggingface.co/allura-org/Q3-30B-A3B-Designant,5/26/2025,11/11/2025,chatml,3.0,30.0,30.0,TRUE,TRUE,FALSE,NA,32.91,4.1,1.6,1.9,6.2,6.0,6.5,17.14,25.24,6.21,19.96,23.67,0.1935,0.1477,0.1423,0.1959,0.3187,-13.0%,62.2%,44.8%,47.8%,57.2%,39.8%,60.8%,35.0%,40.0%,36.9%,36.7%,52.9%,59.0%,31.5%,50.2%,50.2%,71.2%,Liberalism,False,0,20,Qwen3MoeForCausalLM,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,1.28,0.611,0.256,61.2,8043.0,154.7,23.98,NA,NA
-schonsense/Diagesis,https://huggingface.co/schonsense/Diagesis,11/9/2025,11/11/2025,llama-3,70.0,70.0,70.0,TRUE,TRUE,FALSE,NA,35.47,2.9,2.6,3.4,5.5,6.0,5.0,24.71,34.4,27.93,11.79,29.37,0.0585,0.1283,0.0993,0.067,0.2364,-0.9%,53.0%,40.1%,42.3%,58.4%,57.7%,66.9%,44.8%,57.1%,44.0%,40.0%,31.9%,44.6%,50.4%,56.7%,53.1%,65.4%,Liberalism,False,0,12,LlamaForCausalLM,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,1.46,0.352,0.197,120.3,8966.0,177.3,27.47,NA,NA
+schonsense/Diagesis,https://huggingface.co/schonsense/Diagesis,11/9/2025,11/11/2025,llama-3,70.0,70.0,70.0,TRUE,TRUE,FALSE,32.58,35.47,2.9,2.6,3.4,5.5,6.0,5.0,24.71,34.4,27.93,11.79,29.37,0.0585,0.1283,0.0993,0.067,0.2364,-0.9%,53.0%,40.1%,42.3%,58.4%,57.7%,66.9%,44.8%,57.1%,44.0%,40.0%,31.9%,44.6%,50.4%,56.7%,53.1%,65.4%,Liberalism,False,0,12,LlamaForCausalLM,35.3,0.83,14.1,12.7,0.301,56.0,70.0,0.919,0.464,0.334,1.46,0.352,0.197,120.3,8966.0,177.3,27.47,8.5,8.0
 WokeAI/Tankie-DPE-12b-SFT,https://huggingface.co/WokeAI/Tankie-DPE-12b-SFT,11/10/2025,11/11/2025,chatml,12.0,12.0,12.0,TRUE,FALSE,FALSE,34.98,25.08,1.8,0.9,0.8,7.0,6.0,8.0,17.38,16.39,13.45,22.31,11.05,0.0737,0.1787,0.4125,0.2241,0.2263,-20.1%,61.0%,40.6%,48.1%,62.9%,52.5%,61.7%,35.8%,43.8%,36.5%,36.7%,61.7%,42.5%,40.0%,67.9%,64.8%,56.0%,Liberalism,False,0,0,MistralForCausalLM,26.2,0.73,12.4,6.3,0.258,19.0,36.0,0.848,0.378,0.26,1.573,0.125,0.187,106.4,6911.0,95.6,23.53,3.8,6.4
 soob3123/amoral-gemma3-1B-v2,https://huggingface.co/soob3123/amoral-gemma3-1B-v2,3/25/2025,11/12/2025,gemma-3,1.0,1.0,1.0,TRUE,FALSE,FALSE,13.29,15.4,0.0,0.5,0.3,5.5,7.0,4.0,3.15,6.98,0.0,2.47,3.02,0.0257,0.0579,0.0394,0.0005,NA,-23.8%,61.5%,46.0%,49.6%,66.9%,41.9%,61.0%,41.0%,29.2%,54.0%,32.5%,48.8%,45.4%,54.6%,45.8%,71.0%,83.8%,Liberalism,False,0,0,Gemma3ForCausalLM,17.4,0.82,14.5,9.6,0.241,30.0,0.0,0.903,0.47,0.252,NA,NA,NA,184.7,16054.0,246.5,48.05,0.7,4.6
 soob3123/amoral-gemma3-4B-v2,https://huggingface.co/soob3123/amoral-gemma3-4B-v2,3/31/2025,11/12/2025,gemma-3,4.0,4.0,4.0,TRUE,FALSE,FALSE,14.63,22.82,1.2,1.0,0.5,6.8,8.0,5.5,11.16,16.88,6.21,10.4,8.85,0.0341,0.1516,0.0779,0.045,0.2115,-23.9%,52.2%,46.1%,52.2%,54.5%,44.2%,61.2%,43.8%,61.2%,55.8%,26.2%,47.9%,67.1%,41.5%,48.8%,54.6%,60.2%,Centrism,False,0,0,Gemma3ForConditionalGeneration,17.8,0.79,16.2,10.6,0.218,11.0,28.0,0.9,0.457,0.231,1.72,0.115,0.212,159.8,7881.0,193.7,28.78,2.3,6.5
@@ -887,7 +887,7 @@ nvidia/Nemotron-Cascade-14B-Thinking (thinking=False),https://huggingface.co/nvi
 nvidia/Nemotron-Cascade-14B-Thinking (thinking=True),https://huggingface.co/nvidia/Nemotron-Cascade-14B-Thinking,12/8/2025,1/19/2026,chatml,14.0,14.0,14.0,TRUE,FALSE,FALSE,20.45,26.82,1.8,1.3,2.0,6.0,6.0,6.0,14.29,25.81,3.45,13.61,16.45,0.1083,0.1369,0.1559,0.0985,0.181,-22.2%,71.3%,48.4%,43.3%,61.0%,45.6%,61.9%,52.7%,28.1%,32.7%,25.2%,45.8%,51.5%,32.7%,52.9%,59.8%,70.2%,Liberalism,True,6753,6,Qwen3ForCausalLM,27.9,0.7,13.6,7.0,0.309,122.0,100.0,0.915,0.459,0.354,1.6,0.301,0.149,86.1,8534.0,149.2,26.22,4.5,2.7
 aeon37/Llama-3.3-8B-Instruct-128K-heretic,https://huggingface.co/aeon37/Llama-3.3-8B-Instruct-128K-heretic,1/8/2026,1/20/2026,llama-3,8.0,8.0,8.0,TRUE,FALSE,FALSE,12.17,32.53,1.8,1.7,2.5,7.2,7.0,7.5,16.74,21.66,9.66,18.92,20.05,0.1386,0.1506,0.2259,0.2029,0.2278,-15.0%,61.2%,42.8%,42.6%,59.6%,48.3%,63.5%,40.2%,33.8%,43.5%,39.0%,50.8%,45.0%,31.9%,55.2%,63.5%,60.0%,Liberalism,False,0,1,LlamaForCausalLM,43.4,0.92,10.7,6.5,0.355,16.0,19.0,0.881,0.553,0.328,1.643,0.536,0.304,74.8,7920.0,128.1,23.87,1.8,2.9
 zelk12/MT-Gen4_gemma-3-12B,https://huggingface.co/zelk12/MT-Gen4_gemma-3-12B,1/19/2026,1/20/2026,gemma-3,12.0,12.0,12.0,TRUE,TRUE,FALSE,30.2,21.78,2.4,1.1,1.6,4.0,7.0,1.0,18.43,18.8,12.76,23.73,16.09,0.2056,0.1944,0.3228,0.2208,0.243,-12.8%,61.2%,49.9%,43.7%,61.7%,41.2%,61.7%,52.7%,38.3%,41.7%,36.2%,44.0%,48.3%,38.8%,55.4%,59.4%,70.4%,Liberalism,False,0,0,Gemma3ForConditionalGeneration,34.6,0.75,15.2,6.9,0.285,10.0,68.0,0.885,0.441,0.271,1.553,0.388,0.273,59.0,6450.0,108.8,23.58,4.4,2.5
-yasserrmd/Neuro-Orchestrator-8B,https://huggingface.co/yasserrmd/Neuro-Orchestrator-8B,12/5/2025,1/20/2026,chatml,8.0,8.0,8.0,TRUE,TRUE,FALSE,NA,27.99,1.8,0.9,1.3,7.8,6.0,9.5,10.13,14.19,6.9,9.29,12.51,0.1092,0.1716,0.0805,0.1032,NA,-15.8%,63.0%,45.5%,43.6%,60.4%,49.0%,69.6%,55.0%,33.1%,42.5%,35.4%,49.0%,46.7%,35.2%,50.6%,61.2%,69.4%,Liberalism,True,3983,13,Qwen3ForCausalLM,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,85.7,7140.0,191.4,26.07,NA,NA
+yasserrmd/Neuro-Orchestrator-8B,https://huggingface.co/yasserrmd/Neuro-Orchestrator-8B,12/5/2025,1/20/2026,chatml,8.0,8.0,8.0,TRUE,TRUE,FALSE,23.36,27.99,1.8,0.9,1.3,7.8,6.0,9.5,10.13,14.19,6.9,9.29,12.51,0.1092,0.1716,0.0805,0.1032,NA,-15.8%,63.0%,45.5%,43.6%,60.4%,49.0%,69.6%,55.0%,33.1%,42.5%,35.4%,49.0%,46.7%,35.2%,50.6%,61.2%,69.4%,Liberalism,True,3983,13,Qwen3ForCausalLM,35.8,0.84,13.7,7.1,0.331,65.0,75.0,0.881,0.456,0.311,NA,NA,NA,85.7,7140.0,191.4,26.07,1.8,3.4
 nvidia/NVIDIA-Nemotron-Nano-9B-v2 (nemotron-elastic),https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2,8/12/2025,1/19/2026,nemotron-elastic,9.0,9.0,9.0,FALSE,FALSE,TRUE,NA,13.49,1.2,1.3,1.4,1.5,2.0,1.0,18.53,28.56,14.83,12.21,13.02,0.0906,0.2162,0.0914,0.0518,0.1603,-16.6%,65.8%,47.5%,41.8%,57.0%,48.1%,57.3%,48.3%,35.4%,37.9%,29.4%,45.0%,51.0%,30.2%,53.8%,56.2%,61.7%,Liberalism,True,4034,27,NemotronHForCausalLM,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,1.648,0.433,0.151,95.0,5900.0,182.7,28.32,NA,NA
 nvidia/NVIDIA-Nemotron-Nano-9B-v2 (nemotron-elastic (no-think)),https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2,8/12/2025,1/19/2026,nemotron-elastic (no-think),9.0,9.0,9.0,FALSE,FALSE,TRUE,NA,16.86,1.2,1.2,0.8,3.8,6.0,1.5,12.1,25.28,1.72,9.31,10.42,0.056,0.1515,0.057,0.2008,NA,-19.3%,67.8%,49.7%,44.5%,57.3%,39.6%,55.0%,42.5%,37.9%,29.2%,29.6%,55.4%,48.3%,30.0%,57.5%,56.7%,57.7%,Liberalism,False,0,15,NemotronHForCausalLM,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,123.2,7886.0,216.6,23.9,NA,NA
 TheDrummer/Anubis-70B-v1.2,https://huggingface.co/TheDrummer/Anubis-70B-v1.2,1/12/2026,1/23/2026,llama-3,70.0,70.0,70.0,TRUE,FALSE,FALSE,45.47,40.81,2.9,3.8,3.5,6.0,6.0,6.0,29.68,35.76,28.62,24.67,34.82,0.2652,0.1604,0.2288,0.2992,0.2798,-12.2%,62.2%,45.1%,43.3%,60.8%,47.9%,64.6%,47.9%,40.6%,36.0%,36.7%,44.6%,44.4%,40.8%,61.2%,60.4%,60.8%,Liberalism,False,0,0,LlamaForCausalLM,51.0,0.88,14.2,6.3,0.312,16.0,76.0,0.855,0.436,0.284,1.447,0.279,0.265,49.9,7536.0,127.4,22.53,3.3,5.9
@@ -941,4 +941,4 @@ ddh0/Cassiopeia-70B,https://huggingface.co/ddh0/Cassiopeia-70B,7/18/2025,2/1/202
 zerofata/L3.3-GeneticLemonade-Opus-70B,https://huggingface.co/zerofata/L3.3-GeneticLemonade-Opus-70B,7/8/2025,2/1/2026,llama-3,70.0,70.0,70.0,True,True,False,42.42,42.55,4.1,2.9,5.1,5.2,6.0,4.5,33.23,41.28,31.72,26.7,39.44,0.3879,0.1688,0.147,0.2841,0.3472,-16.2%,65.1%,46.7%,42.7%,63.0%,44.0%,65.0%,49.2%,39.8%,31.2%,33.8%,45.0%,45.0%,38.1%,61.2%,63.1%,64.6%,Liberalism,False,0,0,LlamaForCausalLM,26.3,0.86,14.5,5.5,0.313,24.0,59.0,0.892,0.432,0.269,1.38,0.203,0.338,37.7,7237.0,152.8,22.72,4.4,5.4
 Delta-Vector/Austral-70B-Winton,https://huggingface.co/Delta-Vector/Austral-70B-Winton,6/25/2025,2/1/2026,llama-3,70.0,70.0,70.0,True,False,False,38.94,41.65,4.1,2.7,4.5,5.8,6.0,5.5,29.41,37.38,30.0,20.85,36.69,0.2598,0.1547,0.0875,0.2424,0.298,-11.7%,60.9%,49.4%,44.7%,61.8%,40.4%,62.1%,50.8%,42.5%,37.7%,37.1%,45.8%,41.7%,46.7%,61.5%,60.8%,63.1%,Liberalism,False,0,0,LlamaForCausalLM,39.4,0.86,14.8,6.3,0.316,26.0,71.0,0.904,0.455,0.24,1.443,0.368,0.318,50.6,7755.0,185.7,23.27,7.1,8.7
 zai-org/GLM-4.7-Flash (glm-4.7 (no-think)),https://huggingface.co/zai-org/GLM-4.7-Flash,1/19/2026,2/1/2026,glm-4.7 (no-think),3.0,30.0,30.0,False,False,True,22.45,27.03,1.2,1.4,1.0,7.5,7.0,8.0,19.64,23.85,16.9,18.17,12.04,0.0664,0.1551,0.2489,0.2533,0.1846,-12.4%,56.7%,50.8%,47.9%,55.7%,42.3%,53.5%,48.3%,47.1%,47.1%,35.8%,50.6%,50.0%,43.1%,47.3%,54.2%,65.6%,Centrism,False,0,7,Glm4MoeLiteForCausalLM,32.2,0.74,11.3,5.0,0.362,48.0,98.0,0.845,0.437,0.38,1.71,0.157,0.165,112.5,7740.0,122.8,23.12,4.1,5.5
-zai-org/GLM-4.7-Flash (glm-4.7 w/ <think> prefill),https://huggingface.co/zai-org/GLM-4.7-Flash,1/19/2026,2/1/2026,glm-4.7 w/ <think> prefill,3.0,30.0,30.0,False,False,True,NA,21.54,2.9,2.2,1.3,2.2,3.0,1.5,20.31,31.97,11.72,17.25,21.24,0.0794,0.1362,0.2562,0.0782,0.3127,-8.3%,64.9%,43.8%,41.5%,60.1%,50.2%,56.2%,37.9%,39.8%,32.3%,33.3%,41.9%,43.8%,39.0%,66.2%,52.9%,61.0%,Liberalism,True,9250,13,Glm4MoeLiteForCausalLM,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,1.507,0.014,0.295,102.1,8564.0,121.3,26.97,NA,NA
+zai-org/GLM-4.7-Flash (glm-4.7 w/ <think> prefill),https://huggingface.co/zai-org/GLM-4.7-Flash,1/19/2026,2/1/2026,glm-4.7 w/ <think> prefill,3.0,30.0,30.0,False,False,True,14.41,21.54,2.9,2.2,1.3,2.2,3.0,1.5,20.31,31.97,11.72,17.25,21.24,0.0794,0.1362,0.2562,0.0782,0.3127,-8.3%,64.9%,43.8%,41.5%,60.1%,50.2%,56.2%,37.9%,39.8%,32.3%,33.3%,41.9%,43.8%,39.0%,66.2%,52.9%,61.0%,Liberalism,True,9250,13,Glm4MoeLiteForCausalLM,26.7,0.67,11.8,5.4,0.376,169.0,99.0,0.844,0.411,0.393,1.507,0.014,0.295,102.1,8564.0,121.3,26.97,3.2,5.1