Spaces:
Running
Running
| model,model_type,params,license,pass_rate,l1,l2,l3s,l3u | |
| Claude Opus 4.6,Frontier,,Proprietary,90.8,2.4,0.3,2.2,4.2 | |
| GPT-5.3 Codex,Frontier,,Proprietary,89.0,2.7,0.6,2.7,5.0 | |
| Gemini 3.1 Pro,Frontier,,Proprietary,86.3,8.4,0.5,1.2,3.6 | |
| GPT-5.4,Frontier,,Proprietary,81.7,1.2,0.6,6.6,10.0 | |
| GPT-5.2,Frontier,,Proprietary,76.9,0.0,7.6,4.6,11.0 | |
| Claude Sonnet 4.6,Frontier,,Proprietary,76.2,11.3,0.3,5.6,6.7 | |
| GPT-OSS-120B,Frontier,120,Proprietary,69.0,12.2,3.3,8.8,6.6 | |
| GPT-5.1,Frontier,,Proprietary,67.9,6.1,4.0,7.0,15.0 | |
| Gemini 3 Pro,Frontier,,Proprietary,64.4,29.3,0.1,2.0,4.2 | |
| CodeV-R1-Distill-7B,RTL Specialized,7,Open,66.3,2.5,2.7,11.8,16.7 | |
| CodeV-R1-Qwen-7B,RTL Specialized,7,Open,69.7,1.1,2.1,11.5,15.6 | |
| ScaleRTL-Qwen-32B,RTL Specialized,32,Open,75.0,1.5,1.5,12.0,10.0 | |
| Qwen2.5-Coder-7B,Open Source,7,Open,11.9,57.4,6.5,4.4,19.7 | |
| Qwen2.5-Coder-32B,Open Source,32,Open,15.4,56.5,4.6,2.6,20.9 | |
| DS-R1-Distill-32B,Open Source,32,Open,49.0,24.7,11.0,5.3,10.0 | |
| K2-Think-SFT,Open Source,,Open,64.5,15.4,6.9,4.0,9.1 | |
| K2-Think,Open Source,,Open,67.1,12.3,6.5,5.7,8.3 | |
| K2-Think-SFT (RL),Open Source,,Open,71.8,7.4,4.2,6.4,10.2 | |
| K2-Think (RL),Open Source,,Open,73.1,7.8,2.5,7.1,9.6 | |