Embodied vision-language reasoning on Human evaluations H
0.879ScoreQwen3-VL-235B-A22B-Thinking
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-VL-235B-A22B-ThinkingParameters=235B-A22B, Variant=Thinking2026.02 | 0.879 | |
| GPT-5-20250807-MiniVersion=20250807, Size=Mini2026.02 | 0.794 | |
| Qwen3-VL-235B-A22B-InstructParameters=235B-A22B, Variant=Instruct2026.02 | 0.774 | |
| Qwen3-VL-30B-A3B-ThinkingParameters=30B-A3B, Variant=Thinking2026.02 | 0.712 | |
| Internvl-3.5-38BParameters=38B2026.02 | 0.645 | |
| Internvl-3.5-241B-A28BParameters=241B-A28B2026.02 | 0.636 | |
| Qwen3-VL-30B-A3B-InstructParameters=30B-A3B, Variant=Instruct2026.02 | 0.625 | |
| Internvl-3.5-8BParameters=8B2026.02 | 0.615 | |
| Qwen2.5-VL-72B-InstructParameters=72B, Variant=Instruct2026.02 | 0.613 | |
| Qwen2.5-VL-32B-InstructParameters=32B, Variant=Instruct2026.02 | 0.585 | |
| Qwen2.5-VL-7B-InstructParameters=7B, Variant=Instruct2026.02 | 0.555 | |
| Internvl-3.5-30B-A3BParameters=30B-A3B2026.02 | 0.553 | |
| Qwen2.5-VL-3B-InstructParameters=3B, Variant=Instruct2026.02 | 0.504 |