List your company
ResearchFormerly WizWand

Visual Question Answering on OmniMedVQA BRIGHT Challenge

90.11AccuracyPatho-AgenticRAG
-2.08621.849545.78569.7205May 16, 2025Jul 16, 2025Sep 15, 2025Nov 15, 2025Jan 15, 2026Mar 17, 2026May 18, 2026
Updated 4mo ago

Evaluation results

MethodLinks
Patho-AgenticRAG2025.0890.11
Patho-AgenticRAG2026.0590.1
PathoSageHost Model=GPT-4o2026.0588.3
Gemini-1.5-Flash-Preview2026.0570.8
Patho-R12026.0570.8
Patho-R1-7BModel Size=Large, Thinking Ability=With2025.0570.79
Patho-R1-7B2025.0870.79
Patho-R1-3BModel Size=Small, Thinking Ability=With2025.0569.89
InternVL3-8BModel Size=Large, Thinking Ability=With2025.0565.28
InternVL3-8B2025.0865.28
Qwen2-VL-72B-Instruct2026.0561.6
GPT-4o-mini2026.0556.9
Qwen2.5VL-3BModel Size=Small, Thinking Ability=With2025.0555.39
Llama-3.2V-11B-cotModel Size=Large, Thinking Ability=With2025.0554.83
Llama-3.2V-11B-cotReasoning=Chain-of-Thought2025.0854.83
Qwen2-VL-8B-Instruct2026.0554.7
HuatuoGPT-Vision-7BModel Size=Large, Thinking Ability=Without2025.0552.47
InternVL2-8B2026.0549.8
InternVL2.5-8BModel Size=Large, Thinking Ability=With2025.0549.78
InternVL2.5-8B2025.0849.78
Llama-3.2-11B-Vision-InstructModel Size=Large, Thinking Ability=With2025.0547.08
Llama-3.2-11B-VI2025.0847.08
Llama3.2-3B-vlModel Size=Small, Thinking Ability=Without2025.0546.4
PathGen-LLaVA-13BModel Size=Large, Thinking Ability=Without2025.0546.07
VILA1.5-3BModel Size=Small, Thinking Ability=Without2025.0543.6
Qwen2.5VL-7BModel Size=Large, Thinking Ability=With2025.0543.6
Qwen2.5VL-7B2025.0843.6
InternVL2.5-8B2026.0540.6
InternVL2-8BModel Size=Large, Thinking Ability=With2025.0540.56
InternVL2-8B2025.0840.56
DeepSeek-VL2-TinyModel Size=Small, Thinking Ability=With2025.0535.84
Quilt-LLaVA-v1.5-7BModel Size=Large, Thinking Ability=Without2025.0534.27
LLaVA-Onevision-7B2026.0531.5
LLaVA-Onevision-7BModel Size=Large, Thinking Ability=With2025.0531.46
LLaVA-Onevision-7B2025.0831.46
LLaVA-Med-v1.5-Mistral-7BModel Size=Large, Thinking Ability=Without2025.0527.75
Paligemma2-3b-pt-224Model Size=Small, Thinking Ability=Without2025.051.46