List your company
ResearchFormerly WizWand

Medical Question Answering on HLE-Med (test)

28.19AccuracyTongyi-DeepResearch-30BA3B
10.936415.415719.89524.3743Jan 26, 2026
Updated 8mo ago

Evaluation results

MethodLinks
Tongyi-DeepResearch-30BA3BModel Group=DeepResearch Models2026.0128.19
DEEPMED-14B-RLModel Group=DeepResearch Models, Training Stage=RL2026.0126.84
MedResaon-8BModel Group=Medical Reasoning Models2026.0122.4
Deepseek-v3.2-685BModel Group=Awesome General Models2026.0119.46
DEEPMED-14B-SFTModel Group=DeepResearch Models, Training Stage=SFT2026.0119.46
Kimi-K2-Thinking-1TBModel Group=Awesome General Models2026.0118.79
M1-1K-32BModel Group=Medical Reasoning Models2026.0116.78
BaiChuan-M2-32BModel Group=Medical Reasoning Models2026.0116.78
Qwen3-30BA3B-ThinkingModel Group=Awesome General Models2026.0114.77
M1-1K-7BModel Group=Medical Reasoning Models2026.0114.77
Gemini2.5-ProModel Group=Awesome General Models2026.0114.36
Qwen3-14BModel Group=Awesome General Models2026.0112.75
HuatuoGPT-o1-70BModel Group=Medical Reasoning Models2026.0111.6