List your company

Multimodal Reasoning Accuracy on MM-Vet

76.2Pass@1 AccuracyInternVL3-9B
52.2858.4964.770.91Apr 11, 2026

Evaluation results

MethodLinks
InternVL3-9BModel Source Category=Open-Source Models2026.0476.2—
Qwen2.5-VL-7B-Instruct + RFTModel Source Category=Ours, Training Strategy=RFT2026.0473.8—
Claude-3.5-SonnetModel Source Category=Closed-Source Models2026.0470.1—
GPT-4o-20240513Model Source Category=Closed-Source Models2026.0469.1—
GPT-4VModel Source Category=Closed-Source Models2026.0467.5—
Qwen2.5-VL-7B-InstructModel Source Category=Base Model, Chain-of-Thought (CoT)=true2026.0467.2—
Qwen2.5-VL-7B-InstructModel Source Category=Base Model2026.0467.1—
Qwen2.5-VL-7B-InstructModel Source Category=Ours2026.0467.1—
InternVL2.5-26BModel Source Category=Open-Source Models2026.0465—
Qwen2.5-VL-7B-Instruct + cold startModel Source Category=Ours, Training Strategy=cold start2026.0464.2—
Gemini-1.5-ProModel Source Category=Closed-Source Models2026.0464—
InternVL2.5-8BModel Source Category=Open-Source Models2026.0462.8—
Qwen2-VL-7BModel Source Category=Open-Source Models2026.0462—
LLaVA-OneVision-72BModel Source Category=Open-Source Models2026.0460.6—
MiniCPM-V2.6Model Source Category=Open-Source Models2026.0460—
Cambrian-34BModel Source Category=Open-Source Models2026.0453.2—
Imp-v1LM=Phi-2-2.7B, Res.=3842024.12—33.1
LLaVA-1.5LM=Vicuna-7B, Res.=3362024.12—30.5
LLaVA-PhiLM=Phi-2-2.7B, Res.=3362024.12—28.9
Mipha-3BLM=Phi-2-2.7B, Res.=3842024.12—32.1
MoE-LLaVA-3.6BLM=Phi-2-2.7B, Res.=3842024.12—35.9
mPLUG-Owl2LM=LLaMA-7B, Res.=4482024.12—36.2
OlympusLM=Phi-2-2.7B, Res.=3842024.12—33.8
TinyLLaVALM=Phi-2-2.7B, Res.=3842024.12—32