Embodied vision-language reasoning on Original benchmark B
61.26ScoreQwen3-VL-235B-A22B-Thinking
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Qwen3-VL-235B-A22B-ThinkingParameters=235B-A22B, Variant=Thinking2026.02 | 61.26 | — | — | |
| Internvl-3.5-241B-A28BParameters=241B-A28B2026.02 | 56.76 | — | — | |
| Qwen3-VL-235B-A22B-InstructParameters=235B-A22B, Variant=Instruct2026.02 | 55.39 | — | — | |
| GPT-5-20250807-MiniVersion=20250807, Size=Mini2026.02 | 55.16 | — | — | |
| Internvl-3.5-38BParameters=38B2026.02 | 55.01 | — | — | |
| Qwen3-VL-30B-A3B-ThinkingParameters=30B-A3B, Variant=Thinking2026.02 | 54.14 | — | — | |
| Internvl-3.5-30B-A3BParameters=30B-A3B2026.02 | 51.38 | — | — | |
| Qwen2.5-VL-72B-InstructParameters=72B, Variant=Instruct2026.02 | 51.07 | — | — | |
| Internvl-3.5-8BParameters=8B2026.02 | 48.84 | — | — | |
| Qwen3-VL-30B-A3B-InstructParameters=30B-A3B, Variant=Instruct2026.02 | 48.36 | — | — | |
| Qwen2.5-VL-32B-InstructParameters=32B, Variant=Instruct2026.02 | 47.24 | — | — | |
| Qwen2.5-VL-7B-InstructParameters=7B, Variant=Instruct2026.02 | 44.26 | — | — | |
| Qwen2.5-VL-3B-InstructParameters=3B, Variant=Instruct2026.02 | 37.62 | — | — | |
| Ranking correlation with Human (H)Type=Correlation Analysis2026.02 | — | 0.83 | 0.64 |