List your company

Medical Diagnosis on VeriSim Noisy Levels 1-3

69.2Top-1 AccuracyQwen-2.5-72B
32.07241.71151.3560.989Apr 12, 2026

Evaluation results

MethodLinks
Qwen-2.5-72BSize=72B, Type=General2026.0469.2-15.334.5
Llama-3.1-70BSize=70B, Type=General2026.0465.5-16.635.3
OpenBioLLM-70BSize=70B, Type=Medical2026.0463.1-16.136
Meditron-70BSize=70B, Type=Medical2026.0462.8-15.635.2
BioMistral-7BSize=7B, Type=Medical2026.0441.8-22.450
Llama-3.1-8BSize=8B, Type=General2026.0440.2-21.648.8
Mistral-7BSize=7B, Type=General2026.0433.5-24.555.1