List your company

General Multimodal Evaluation on MMVet turbo

69.7Overall ScoreD2Djus
53.5857.76561.9566.135Jul 9, 2025

Evaluation results

MethodLinks
D2DjusReasoning Strategy=D2D, Variant=jus, Backbone=Qwen2.5-VL-7B2025.0769.7
GPT-4o2025.0769.1
D2IlocReasoning Strategy=D2I, Variant=loc, Backbone=Qwen2.5-VL-7B2025.0767.9
GPT-4V2025.0767.5
R1-Onevision-7B2025.0767.5
Qwen2.5-VL-7B*Backbone=Qwen2.5-VL-7B2025.0767.1
D2IjusReasoning Strategy=D2I, Variant=jus, Backbone=Qwen2.5-VL-7B2025.0766.9
D2DparReasoning Strategy=D2D, Variant=par, Backbone=Qwen2.5-VL-7B2025.0766.4
D2DlocReasoning Strategy=D2D, Variant=loc, Backbone=Qwen2.5-VL-7B2025.0765.3
D2IparReasoning Strategy=D2I, Variant=par, Backbone=Qwen2.5-VL-7B2025.0765.3
InternVL2.5-8B2025.0762.8
Qwen2-VL-7B2025.0762
Qwen2.5-VL-7B w/ GRPOReasoning Mode=Deliberate, Backbone=Qwen2.5-VL-7B2025.0760.8
LLaVA-CoT-11B2025.0760.3
Qwen2.5-VL-7B w/ GRPO†Reasoning Mode=Intuitive, Backbone=Qwen2.5-VL-7B2025.0758.6
InternVL2-8B2025.0754.2