| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| AppWorld (test-normal) | ACON UTCO | Accuracy56.5 | 22 | 1mo ago | |
| τ2-bench Airline | SagaLLM | Success Rate97 | 22 | 1mo ago | |
| τ2-Bench | Airline Success Rate84 | 19 | 1mo ago | ||
| τ-bench Average | IG-clarifier | Success Rate40 | 18 | 1mo ago | |
| ScienceWorld | SPARK | L0 Score75 | 18 | 4mo ago | |
| ALFWorld | SPARK | Look Success100 | 18 | 4mo ago | |
| AppWorld Challenge (test) | Task Goal Completion (TGC)49.88 | 13 | 3mo ago | ||
| AppWorld LeaderBoard | ReAct | Greedy Success Rate48.8 | 13 | 4mo ago | |
| AppWorld normal Hard (test) | Accuracy39.7 | 11 | 1mo ago | ||
| AppWorld Easy normal (test) | ACON UTCO | Accuracy86 | 11 | 1mo ago | |
| Terminal-Bench Hard 2 (30 tasks) | Pass@156.7 | 7 | 2mo ago | ||
| Terminal-Bench Med. 2 (55 tasks) | AHE | Pass@188.2 | 7 | 2mo ago | |
| Terminal-Bench Easy 4 tasks 2 | TF-GRPO | Pass@1100 | 7 | 2mo ago | |
| Terminal-Bench All 2 | AHE | Pass@177 | 7 | 2mo ago | |
| τ2-bench Retail | RAC | Success Rate100 | 4 | 2mo ago | |
| τ2-bench Telecom | SagaLLM | Success Rate100 | 3 | 2mo ago |