Step Execution on Multimodal-Mind2Web
66Step Success RateUI-TARS-7B w/ GPT-4.1
Evaluation Results
| Method | Links | |
|---|---|---|
| UI-TARS-7B w/ GPT-4.1Params=7B w/ -2026.03 | 66 | |
| UI-TARS-7B w/ TraceR1Params=7B w/ 8B2026.03 | 65.3 | |
| UI-TARS-32BParams=32B2026.03 | 64.7 | |
| UI-TARS-7BParams=7B2026.03 | 63.1 | |
| UI-TARS-2BParams=2B2026.03 | 53.1 | |
| Claude-computer-useParams=-2026.03 | 52.5 | |
| OmniParser-v2.0 w/ GPT-4oParams=-2026.03 | 41.3 | |
| GPT-4oParams=-2026.03 | 4.3 |