General Multimodal Evaluation on MMVet turbo
69.7Overall ScoreD2Djus
Evaluation Results
| Method | Links | |
|---|---|---|
| D2DjusReasoning Strategy=D2D, Variant=jus, Backbone=Qwen2.5-VL-7B2025.07 | 69.7 | |
| GPT-4o2025.07 | 69.1 | |
| D2IlocReasoning Strategy=D2I, Variant=loc, Backbone=Qwen2.5-VL-7B2025.07 | 67.9 | |
| GPT-4V2025.07 | 67.5 | |
| R1-Onevision-7B2025.07 | 67.5 | |
| Qwen2.5-VL-7B*Backbone=Qwen2.5-VL-7B2025.07 | 67.1 | |
| D2IjusReasoning Strategy=D2I, Variant=jus, Backbone=Qwen2.5-VL-7B2025.07 | 66.9 | |
| D2DparReasoning Strategy=D2D, Variant=par, Backbone=Qwen2.5-VL-7B2025.07 | 66.4 | |
| D2DlocReasoning Strategy=D2D, Variant=loc, Backbone=Qwen2.5-VL-7B2025.07 | 65.3 | |
| D2IparReasoning Strategy=D2I, Variant=par, Backbone=Qwen2.5-VL-7B2025.07 | 65.3 | |
| InternVL2.5-8B2025.07 | 62.8 | |
| Qwen2-VL-7B2025.07 | 62 | |
| Qwen2.5-VL-7B w/ GRPOReasoning Mode=Deliberate, Backbone=Qwen2.5-VL-7B2025.07 | 60.8 | |
| LLaVA-CoT-11B2025.07 | 60.3 | |
| Qwen2.5-VL-7B w/ GRPO†Reasoning Mode=Intuitive, Backbone=Qwen2.5-VL-7B2025.07 | 58.6 | |
| InternVL2-8B2025.07 | 54.2 |