Multimodal Agent Performance on V*
80.6AccuracyBaseline
Evaluation Results
| Method | Links | |
|---|---|---|
| BaselineBackbone=235B-FP8, Training regime=None2026.06 | 80.6 | |
| ToolGateBackbone=235B-FP8, Training regime=Cross-domain2026.06 | 80.1 | |
| ToolGateBackbone=30B, Training regime=In-domain2026.06 | 79.1 | |
| ToolGateBackbone=30B, Training regime=Cross-domain2026.06 | 76.4 | |
| BaselineBackbone=30B, Training regime=None2026.06 | 75.9 |