| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TimeWarp Wiki Environment v1:6 | Success Rate100 | 28 | 2mo ago | ||
| Mind2Web Cross-Domain 1.0 | DuSAR | Success Rate445 | 26 | 3mo ago | |
| Mind2Web Cross-Task 1.0 | PolySkill (+Update) | Success Rate49.2 | 26 | 3mo ago | |
| WebArena | DRIVE | Success Rate45.9 | 19 | 8d ago | |
| Mind2Web All 1.0 | DuSAR | Element Accuracy0.484 | 16 | 3mo ago | |
| MiniWoB (full) | Success Rate77.1 | 10 | 1mo ago | ||
| WorkArena L2 147-task (test) | Success Rate40 | 10 | 1mo ago | ||
| WorkArena L1 (full) | Success Rate79.4 | 10 | 1mo ago | ||
| WebArena (test) | Success Rate53.8 | 10 | 1mo ago | ||
| Mind2Web OOD (test) | SkillFlow | Step Accuracy51.56 | 9 | 19d ago | |
| WebArena Lite | CATTS (entropy, best) | Success Rate47.9 | 9 | 3mo ago | |
| Mind2Web (Cross-Website) | ReasoningBank | Execution Accuracy (EA)46.1 | 8 | 2mo ago | |
| TimeWarp Overall Average v1:6 | Success Rate97.1 | 8 | 2mo ago | ||
| XBench | WebAggregator | Pass@158 | 7 | 1mo ago | |
| VisualWebArena (test) | Success Rate47.9 | 7 | 1mo ago | ||
| BookingArena 1.0 (test) | UI-TARS | Booking.com Success Rate66.7 | 5 | 3mo ago |