Step Execution on Multimodal-Mind2Web
66Step Success Rate
UI-TARS-7B w/ GPT-4.1
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.03 | 66 | |
2026.03 | 65.3 | |
2026.03 | 64.7 | |
2026.03 | 63.1 | |
2026.03 | 53.1 | |
2026.03 | 52.5 | |
2026.03 | 41.3 | |
2026.03 | 4.3 |
UI-TARS-7B w/ GPT-4.1
| Method | Links | |
|---|---|---|
2026.03 | 66 | |
2026.03 | 65.3 | |
2026.03 | 64.7 | |
2026.03 | 63.1 | |
2026.03 | 53.1 | |
2026.03 | 52.5 | |
2026.03 | 41.3 | |
2026.03 | 4.3 |