| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| WebArena | IBM CUGA | Overall Success Rate61.7 | 138 | 16d ago | |
| WebVoyager | FaraGen1.5 Solver (GPT-5.4) | Success Rate93.4 | 81 | 1mo ago | |
| Mind2Web Cross-Domain | GUICrafter-7B | Element Accuracy (EA)68.4 | 64 | 25d ago | |
| WebShop | SAPO | Average Score90.5 | 55 | 1mo ago | |
| Mind2Web | Triton-GRPO-32B | Overall Success Rate58.7 | 41 | 1mo ago | |
| WebShop (test) | 3SPO | Score91.37 | 36 | 1mo ago | |
| WebArena Lite | Qwen3-30B-A3B | Average Success Rate61.8 | 31 | 1mo ago | |
| WebVoyager OOD | Vanilla | Allrecipes56.3 | 30 | 29d ago | |
| Mind2Web All | GUICrafter-7B | Element Accuracy70 | 27 | 25d ago | |
| WebShop Source | MemoryBank | Success Rate100 | 27 | 4mo ago | |
| WebWalkerQA | Experience Internalization | Internalized Inference35 | 26 | 1mo ago | |
| WebWalker Hard | ReAct | Success Rate (SR)30 | 25 | 1mo ago | |
| WebWalker Medium | Reflexion | Success Rate (SR)51.43 | 25 | 1mo ago | |
| WebWalker Easy | WebWalker | Success Rate58.75 | 25 | 1mo ago | |
| MM-Mind2Web | Step Success Rate (SR)22.97 | 22 | 2mo ago | ||
| Mind2Web-SC | Task Success Rate (TSR)33.3 | 20 | 1mo ago | ||
| WebArena Lite v2 | GPT-4o + ScaleCUA-7B | Average Success Rate28.6 | 19 | 1mo ago | |
| WebShop Drift II | Vanilla + GLOVE | Success Rate95 | 18 | 4mo ago | |
| WebShop Drift I | Generative Agent + GLOVE | Success Rate95 | 18 | 4mo ago | |
| WebShop Drift II - Semantic Shift | Voyager + GLOVE | Success Rate95 | 18 | 4mo ago | |
| WebShop Drift I - Semantic Shift | Vanilla + GLOVE | Success Rate95 | 18 | 4mo ago | |
| Mind2Web Live (test) | Task Completion Rate52.8 | 16 | 4mo ago | ||
Success Rate (SR)6.7 | 15 | 1mo ago | |||
| Classifieds | Success Rate13.7 | 15 | 1mo ago | ||
| Mind2Web Service | Mem-W-8B | Success Rate36.27 | 15 | 2mo ago |