Auto-update results.csv

results.csv

@@ -14,6 +14,15 @@ 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,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,500.0,0.0,0.472,882330271.0,0.0,6689285.0,889019556.0,174288.0,410828.0,45.91,1764660.0,0.0,13378.0,1778039.0,0.09,821.0,348.0
 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,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,500.0,1.0,0.41,724984042.0,0.0,5941303.0,730925345.0,93088.0,518565.0,21.02,1449968.0,0.0,11882.0,1461850.0,0.04,1037.0,186.0
 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,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,500.0,6.0,0.498,996839122.0,0.0,7196671.0,1004035793.0,144084.0,446845.0,32.53,1993678.0,0.0,14393.0,2008071.0,0.07,893.0,288.0
+RH SWE-Bench,rounakbende/rh-swe-bench,357,https://huggingface.co/datasets/rounakbende/rh-swe-bench,Claude Code,[],False,https://github.com/anthropics/claude-code,Qwen3.6-27B-FP8,RedHatAI/Qwen3.6-27B-FP8,True,27,fp8,https://huggingface.co/RedHatAI/Qwen3.6-27B-FP8,harbor,https://github.com/harbor-framework/harbor,357.0,9.0,0.493,885869433.0,0.0,4763916.0,890633349.0,201374.0,401657.0,73.84,2481426.0,0.0,13344.0,2494771.0,0.21,1125.0,564.0
+RH SWE-Bench,rounakbende/rh-swe-bench,357,https://huggingface.co/datasets/rounakbende/rh-swe-bench,OpenCode,[],True,https://github.com/opencode-ai/opencode,Qwen3.6-27B-FP8,RedHatAI/Qwen3.6-27B-FP8,True,27,fp8,https://huggingface.co/RedHatAI/Qwen3.6-27B-FP8,harbor,https://github.com/harbor-framework/harbor,357.0,10.0,0.44,410001939.0,0.0,2851571.0,412853510.0,115135.0,315451.0,42.22,1148464.0,0.0,7987.0,1156452.0,0.12,883.0,322.0
+RH SWE-Bench,rounakbende/rh-swe-bench,357,https://huggingface.co/datasets/rounakbende/rh-swe-bench,Pi,[],True,https://github.com/plandex-ai/plandex,Qwen3.6-27B-FP8,RedHatAI/Qwen3.6-27B-FP8,True,27,fp8,https://huggingface.co/RedHatAI/Qwen3.6-27B-FP8,harbor,https://github.com/harbor-framework/harbor,357.0,1.0,0.468,560672462.0,0.0,3618673.0,564291135.0,114791.0,333385.0,42.09,1570511.0,0.0,10136.0,1580647.0,0.12,933.0,321.0
+SWE-Bench Pro -- Ansible,scale-ai/swe-bench-pro,96,https://huggingface.co/datasets/scale-ai/swe-bench-pro,Claude Code,[],False,https://github.com/anthropics/claude-code,Qwen3.6-27B-FP8,RedHatAI/Qwen3.6-27B-FP8,True,27,fp8,https://huggingface.co/RedHatAI/Qwen3.6-27B-FP8,harbor,https://github.com/harbor-framework/harbor,96.0,8.0,0.521,386929017.0,0.0,1847087.0,388776104.0,118693.0,137736.0,43.52,4030510.0,0.0,19240.0,4049751.0,0.45,1434.0,1236.0
+SWE-Bench Pro -- Ansible,scale-ai/swe-bench-pro,96,https://huggingface.co/datasets/scale-ai/swe-bench-pro,OpenCode,[],True,https://github.com/opencode-ai/opencode,Qwen3.6-27B-FP8,RedHatAI/Qwen3.6-27B-FP8,True,27,fp8,https://huggingface.co/RedHatAI/Qwen3.6-27B-FP8,harbor,https://github.com/harbor-framework/harbor,96.0,0.0,0.573,344853232.0,0.0,1661197.0,346514429.0,118356.0,196235.0,43.4,3592221.0,0.0,17304.0,3609525.0,0.45,2044.0,1232.0
+SWE-Bench Pro -- Ansible,scale-ai/swe-bench-pro,96,https://huggingface.co/datasets/scale-ai/swe-bench-pro,Pi,[],True,https://github.com/plandex-ai/plandex,Qwen3.6-27B-FP8,RedHatAI/Qwen3.6-27B-FP8,True,27,fp8,https://huggingface.co/RedHatAI/Qwen3.6-27B-FP8,harbor,https://github.com/harbor-framework/harbor,96.0,0.0,0.49,395189021.0,0.0,2206097.0,397395118.0,80305.0,91995.0,29.45,4116552.0,0.0,22980.0,4139532.0,0.31,958.0,836.0
+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,Qwen3.6-27B-FP8,RedHatAI/Qwen3.6-27B-FP8,True,27,fp8,https://huggingface.co/RedHatAI/Qwen3.6-27B-FP8,harbor,https://github.com/harbor-framework/harbor,500.0,3.0,0.694,1005844088.0,0.0,6255800.0,1012099888.0,228858.0,411348.0,83.91,2011688.0,0.0,12511.0,2024199.0,0.17,822.0,457.0
+SWE-Bench Verified,SWE-bench/SWE-bench_Verified,500,https://huggingface.co/datasets/SWE-bench/SWE-bench_Verified,OpenCode,[],True,https://github.com/opencode-ai/opencode,Qwen3.6-27B-FP8,RedHatAI/Qwen3.6-27B-FP8,True,27,fp8,https://huggingface.co/RedHatAI/Qwen3.6-27B-FP8,harbor,https://github.com/harbor-framework/harbor,500.0,8.0,0.642,395291929.0,0.0,3296668.0,398588597.0,92700.0,374913.0,33.99,790583.0,0.0,6593.0,797177.0,0.07,749.0,185.0
+SWE-Bench Verified,SWE-bench/SWE-bench_Verified,500,https://huggingface.co/datasets/SWE-bench/SWE-bench_Verified,Pi,[],True,https://github.com/plandex-ai/plandex,Qwen3.6-27B-FP8,RedHatAI/Qwen3.6-27B-FP8,True,27,fp8,https://huggingface.co/RedHatAI/Qwen3.6-27B-FP8,harbor,https://github.com/harbor-framework/harbor,500.0,7.0,0.694,544070591.0,0.0,4965652.0,549036243.0,130591.0,408706.0,47.88,1088141.0,0.0,9931.0,1098072.0,0.1,817.0,261.0
 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,Opus 4.6,Opus 4.6,False,1000,bf16,https://www.anthropic.com/news/claude-opus-4-6,harbor,https://github.com/harbor-framework/harbor,357.0,0.0,0.633,438501505.0,419608736.0,2823496.0,860933737.0,126529.0,243310.0,434.54,1228295.0,1175374.0,7908.0,2411579.0,1.22,681.0,354.0
 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,Sonnet 4.6,Sonnet 4.6,False,1000,bf16,https://www.anthropic.com/news/claude-sonnet-4-6,harbor,https://github.com/harbor-framework/harbor,357.0,0.0,0.557,500304168.0,479035103.0,4937782.0,984277053.0,150652.0,269008.0,349.77,1401412.0,1341835.0,13831.0,2757078.0,0.98,753.0,421.0
 SWE-Bench Pro -- Ansible,ScaleAI/SWE-bench_Pro,96,https://huggingface.co/datasets/ScaleAI/SWE-bench_Pro,Claude Code,[],False,https://github.com/anthropics/claude-code,Opus 4.8,Opus 4.8,False,1000,bf16,https://www.anthropic.com/news/claude-opus-4-8,harbor,https://github.com/harbor-framework/harbor,96.0,0.0,0.698,192346997.0,186506482.0,2179945.0,381033424.0,32745.0,39030.0,185.66155285,2003614.0,1942775.0,22707.0,3969098.0,1.93,406.0,341.0