General Reasoning on MuirBench
59.2AccuracyDUEL
Evaluation Results
| Method | Links | |
|---|---|---|
| DUELRole=Solver2026.05 | 59.2 | |
| EvoLMM2026.05 | 58.9 | |
| OpenVLThinker-7B2026.05 | 58.8 | |
| Vision-Zero(CLEVR)2026.05 | 58.6 | |
| DUELRole=Challenger2026.05 | 58.6 | |
| MM-UPT2026.05 | 58.5 | |
| VLAA-Thinker-7B2026.05 | 58.2 | |
| Qwen2.5-VL-7B2026.05 | 58 |