| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| BrowseComp | Kimi K2.5 | Score78.4 | 27 | 4mo ago | |
| τ2-Bench | Score91.6 | 20 | 18d ago | ||
| BFCL v4 | Ling-2.6-1T | pass@170.64 | 16 | 1mo ago | |
| Terminal Bench 2.0 | Pass@148.31 | 11 | 18d ago | ||
| SWE-bench Verified | Score73.8 | 10 | 18d ago | ||
| ClawEval | Ling-2.6-flash | Score64.56 | 7 | 1mo ago | |
| GDPval-AA Elo | Elo Score1,462 | 7 | 4mo ago | ||
| Vending-Bench 2 | Score5,478 | 7 | 4mo ago | ||
| Tool-Decathlon | Score46.3 | 7 | 4mo ago | ||
| MCP-Atlas Public Set | Overall Score68 | 7 | 4mo ago | ||
| BrowseComp-ZH | Score76.1 | 7 | 4mo ago | ||
| TauBench V2 | Super | Airline Score56.9 | 5 | 18d ago | |
| Terminal Bench hard | Super | Accuracy25.5 | 5 | 18d ago | |
| SWE-Bench OpenHands | Super | Accuracy59.5 | 4 | 18d ago | |
| tau^2 | Qwen3.5-4B | Score82.1 | 4 | 2mo ago | |
| SWE Verified OpenHands | Pass@169.2 | 4 | 4mo ago |