List your company

Medical Visual Question Answering on MMMU

70AccuracyMedVLThinker-32B RL
29.824840.254950.68561.1151Aug 4, 2025Aug 24, 2025Sep 14, 2025Oct 4, 2025Oct 25, 2025Nov 14, 2025Dec 5, 2025

Evaluation results

MethodLinks
MedVLThinker-32B RLOpen Weights=true, Open Recipe=true, Training Modality=Text-only (m23k), Decoding=Greedy2025.0870
GPT-4oOpen Weights=false, Open Recipe=false, Decoding=Greedy2025.0868.82
Qwen2.5-VL-32B-InstructOpen Weights=true, Open Recipe=false, Decoding=Greedy2025.0863.92
GPT-4o-miniOpen Weights=false, Open Recipe=false, Decoding=Greedy2025.0863.53
Gemme 3 27BOpen Weights=true, Open Recipe=false, Decoding=Greedy2025.0860.78
MedTutor-R1Backbone=Qwen2.5VL-7B-Instruct2025.1258.82
HuatuoGPT-Vision-34BOpen Weights=true, Open Recipe=true, Decoding=Greedy2025.0857.06
MedVLThinker-7B RLOpen Weights=true, Open Recipe=true, Training Modality=Text-only (m23k), Decoding=Greedy2025.0856.86
MedTutor-R1 w/ LLaVA-basedBackbone=LLaVA2025.1256.38
MedTutor-R1 w/o RLReinforcement Learning=disabled2025.1254.73
Qwen2.5-VL-7B-InstructOpen Weights=true, Open Recipe=false, Decoding=Greedy2025.0852.94
Qwen2.5VLBackbone=Qwen2.5VL-7B-Instruct2025.1252.61
MedVLThinker-3B RLOpen Weights=true, Open Recipe=true, Training Modality=Text-only (m23k), Decoding=Greedy2025.0852.16
HuatuoGPT-Vision-7BOpen Weights=true, Open Recipe=true, Decoding=Greedy2025.0850.59
Gemme 3 4BOpen Weights=true, Open Recipe=false, Decoding=Greedy2025.0846.67
Qwen2.5-VL-3B-InstructOpen Weights=true, Open Recipe=false, Decoding=Greedy2025.0844.12
MedGemma 27BOpen Weights=true, Open Recipe=false, Decoding=Greedy2025.0835.88
MedGemma 4BOpen Weights=true, Open Recipe=false, Decoding=Greedy2025.0832.55
Llava Med v1.5 Mistral 7BOpen Weights=true, Open Recipe=true, Decoding=Greedy2025.0831.37