| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| SWE-bench Verified | MiniMax-M2.5 | Resolution Rate89.2 | 110 | 1mo ago | |
| SWE-Bench-Pro (test) | GPT-5.4 | Pass@159.9 | 21 | 1mo ago | |
| SWE-Bench Lite | AIR | Resolution Rate73.5 | 16 | 4mo ago | |
| SWE-Bench Lite | Context Weaver | Pass@153.7 | 10 | 2mo ago | |
| SWE-Bench Multilingual | Nemotron 3 Super | Resolve Rate45.78 | 6 | 3mo ago | |
| SWE-Bench Verified 100-instance | ContextWeaver | Pass@168 | 5 | 2mo ago | |
| Terminal Bench | Hybrid | Resolve Rate32.5 | 4 | 4mo ago | |
| Multi-SWE-Bench Mini | Hybrid | Resolution Rate20 | 4 | 4mo ago | |
| SWE-Bench Live Lite | Hybrid | Resolve Rate0.224 | 4 | 4mo ago | |
| SWE-bench 500 (test) | agyn | Resolution Score72.2 | 4 | 4mo ago |