| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Mind2Web Online (test) | MR | Mean Spearman Rho0.921 | 5 | 23d ago | |
| CoreBench Hard (test) | MR | Mean Spearman Rho0.901 | 5 | 23d ago | |
| tau-bench Airline (test) | MR | Mean Spearman Rho0.944 | 5 | 23d ago | |
| USACO (test) | MR | Mean Spearman Rho0.938 | 5 | 23d ago | |
| SWE-bench Mini (test) | Mean Spearman Rho0.922 | 5 | 23d ago | ||
| GAIA (test) | MR | Mean Spearman Rho0.946 | 5 | 23d ago | |
| TerminalBench (test) | Mean Spearman Rho0.988 | 5 | 23d ago | ||
| SciCode (test) | Mean Spearman Rho0.753 | 4 | 23d ago |