Auto-update results.csv

results.csv

@@ -5,6 +5,15 @@ SWE-Bench Pro -- Ansible,ScaleAI/SWE-bench_Pro,96,https://huggingface.co/dataset
 SWE-Bench Verified,SWE-bench/SWE-bench_Verified,500,https://huggingface.co/datasets/SWE-bench/SWE-bench_Verified,Claude Code,[],False,https://github.com/anthropics/claude-code,Gemma4-31B-FP8,RedHatAI/gemma-4-31B-it-FP8-block,True,31,fp8,https://huggingface.co/RedHatAI/gemma-4-31B-it-FP8-block,harbor,https://github.com/harbor-framework/harbor,500.0,35.0,0.612,651306166.0,0.0,4591859.0,655898025.0,524857.0,669355.0,104.14,1302612.0,0.0,9183.0,1311796.0,0.21,1338.0,1049.0
 SWE-Bench Verified,SWE-bench/SWE-bench_Verified,500,https://huggingface.co/datasets/SWE-bench/SWE-bench_Verified,OpenCode,[],True,https://github.com/anomalyco/opencode,Gemma4-31B-FP8,RedHatAI/gemma-4-31B-it-FP8-block,True,31,fp8,https://huggingface.co/RedHatAI/gemma-4-31B-it-FP8-block,harbor,https://github.com/harbor-framework/harbor,500.0,12.0,0.606,525563275.0,0.0,4183675.0,529746950.0,166092.0,444527.0,52.73,1051126.0,0.0,8367.0,1059493.0,0.11,889.0,332.0
 SWE-Bench Verified,SWE-bench/SWE-bench_Verified,500,https://huggingface.co/datasets/SWE-bench/SWE-bench_Verified,Pi,[],True,https://github.com/earendil-works/pi/tree/main,Gemma4-31B-FP8,RedHatAI/gemma-4-31B-it-FP8-block,True,31,fp8,https://huggingface.co/RedHatAI/gemma-4-31B-it-FP8-block,harbor,https://github.com/harbor-framework/harbor,500.0,0.0,0.574,377479979.0,0.0,4177117.0,381657096.0,122274.0,385336.0,38.82,754959.0,0.0,8354.0,763314.0,0.08,770.0,244.0
+RH SWE-Bench,rounakbende10/rh-swe-bench,357,https://huggingface.co/datasets/rounakbende/rh-swe-bench,Claude Code,[],False,https://docs.anthropic.com/en/docs/claude-code,GPT-OSS-120B,RedHatAI/gpt-oss-120b,True,120,mxfp4,https://huggingface.co/RedHatAI/gpt-oss-120b,harbor,https://github.com/harbor-framework/harbor,357.0,31.0,0.317,1088634865.0,0.0,6200414.0,1094835279.0,398444.0,575536.0,15.05,3049397.0,0.0,17368.0,3066765.0,0.04,1612.0,1116.0
+RH SWE-Bench,rounakbende10/rh-swe-bench,357,https://huggingface.co/datasets/rounakbende/rh-swe-bench,OpenCode,[],True,https://github.com/opencode-ai/opencode,GPT-OSS-120B,RedHatAI/gpt-oss-120b,True,120,mxfp4,https://huggingface.co/RedHatAI/gpt-oss-120b,harbor,https://github.com/harbor-framework/harbor,357.0,7.0,0.294,419671770.0,0.0,2277963.0,421949733.0,98909.0,169021.0,3.74,1175551.0,0.0,6380.0,1181932.0,0.01,473.0,277.0
+RH SWE-Bench,rounakbende10/rh-swe-bench,357,https://huggingface.co/datasets/rounakbende/rh-swe-bench,Pi,[],True,https://github.com/earendil-works/pi/tree/main,GPT-OSS-120B,RedHatAI/gpt-oss-120b,True,120,mxfp4,https://huggingface.co/RedHatAI/gpt-oss-120b,harbor,https://github.com/harbor-framework/harbor,357.0,20.0,0.23,419282595.0,0.0,1954817.0,421237412.0,100632.0,168697.0,3.8,1174461.0,0.0,5475.0,1179936.0,0.01,472.0,281.0
+SWE-Bench Pro,scale-ai/swe-bench-pro,96,https://huggingface.co/datasets/scale-ai/swe-bench-pro,Claude Code,[],False,https://docs.anthropic.com/en/docs/claude-code,GPT-OSS-120B,RedHatAI/gpt-oss-120b,True,120,mxfp4,https://huggingface.co/RedHatAI/gpt-oss-120b,harbor,https://github.com/harbor-framework/harbor,96.0,2.0,0.375,347744043.0,0.0,1903023.0,349647066.0,59653.0,67586.0,2.25,3622333.0,0.0,19823.0,3642156.0,0.02,704.0,621.0
+SWE-Bench Pro,scale-ai/swe-bench-pro,96,https://huggingface.co/datasets/scale-ai/swe-bench-pro,OpenCode,[],True,https://github.com/opencode-ai/opencode,GPT-OSS-120B,RedHatAI/gpt-oss-120b,True,120,mxfp4,https://huggingface.co/RedHatAI/gpt-oss-120b,harbor,https://github.com/harbor-framework/harbor,96.0,1.0,0.333,112041538.0,0.0,781173.0,112822711.0,25086.0,31180.0,0.95,1167099.0,0.0,8137.0,1175236.0,0.01,324.0,261.0
+SWE-Bench Pro,scale-ai/swe-bench-pro,96,https://huggingface.co/datasets/scale-ai/swe-bench-pro,Pi,[],True,https://github.com/earendil-works/pi/tree/main,GPT-OSS-120B,RedHatAI/gpt-oss-120b,True,120,mxfp4,https://huggingface.co/RedHatAI/gpt-oss-120b,harbor,https://github.com/harbor-framework/harbor,96.0,15.0,0.292,125247664.0,0.0,597435.0,125845099.0,75715.0,79741.0,2.86,1304663.0,0.0,6223.0,1310886.0,0.03,830.0,788.0
+SWE-Bench Verified,swe-bench/swe-bench-verified,500,https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified,Claude Code,[],False,https://docs.anthropic.com/en/docs/claude-code,GPT-OSS-120B,RedHatAI/gpt-oss-120b,True,120,mxfp4,https://huggingface.co/RedHatAI/gpt-oss-120b,harbor,https://github.com/harbor-framework/harbor,500.0,13.0,0.376,833651681.0,0.0,5656173.0,839307854.0,150981.0,200547.0,5.7,1667303.0,0.0,11312.0,1678615.0,0.01,401.0,301.0
+SWE-Bench Verified,swe-bench/swe-bench-verified,500,https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified,OpenCode,[],True,https://github.com/opencode-ai/opencode,GPT-OSS-120B,RedHatAI/gpt-oss-120b,True,120,mxfp4,https://huggingface.co/RedHatAI/gpt-oss-120b,harbor,https://github.com/harbor-framework/harbor,500.0,33.0,0.326,202856940.0,0.0,1444371.0,204301311.0,35190.0,322482.0,3.32,405713.0,0.0,2888.0,408602.0,0.01,644.0,70.0
+SWE-Bench Verified,swe-bench/swe-bench-verified,500,https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified,Pi,[],True,https://github.com/earendil-works/pi/tree/main,GPT-OSS-120B,RedHatAI/gpt-oss-120b,True,120,mxfp4,https://huggingface.co/RedHatAI/gpt-oss-120b,harbor,https://github.com/harbor-framework/harbor,500.0,47.0,0.234,90107247.0,0.0,905031.0,91012278.0,146747.0,176174.0,13.86,180214.0,0.0,1810.0,182024.0,0.03,352.0,293.0
 RH SWE-Bench,rounakbende10/rh-swe-bench,357,https://huggingface.co/datasets/rounakbende/rh-swe-bench,Claude Code,[],False,https://github.com/anthropics/claude-code,Nemotron-3-Super-120B-NVFP4,RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4,True,120,nvfp4,https://huggingface.co/RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4,harbor,https://github.com/harbor-framework/harbor,357.0,14.0,0.224,783670817.0,0.0,5510291.0,789181108.0,144352.0,355122.0,38.03,2195156.0,0.0,15434.0,2210591.0,0.11,994.0,404.0
 RH SWE-Bench,rounakbende10/rh-swe-bench,357,https://huggingface.co/datasets/rounakbende/rh-swe-bench,OpenCode,[],True,https://github.com/anomalyco/opencode,Nemotron-3-Super-120B-NVFP4,RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4,True,120,nvfp4,https://huggingface.co/RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4,harbor,https://github.com/harbor-framework/harbor,357.0,7.0,0.308,839586046.0,0.0,5706139.0,845292185.0,94762.0,251102.0,37.44,2351781.0,0.0,15983.0,2367765.0,0.1,703.0,265.0
 RH SWE-Bench,rounakbende10/rh-swe-bench,357,https://huggingface.co/datasets/rounakbende/rh-swe-bench,Pi,[],True,https://github.com/earendil-works/pi/tree/main,Nemotron-3-Super-120B-NVFP4,RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4,True,120,nvfp4,https://huggingface.co/RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4,harbor,https://github.com/harbor-framework/harbor,357.0,13.0,0.216,770574986.0,0.0,6519128.0,777094114.0,116348.0,360934.0,30.65,2158473.0,0.0,18260.0,2176734.0,0.09,1011.0,325.0