List your company

Question Answering on WMDP multiple-choice QA

65.1Bio AccuracyBase
29.32438.61247.957.188Mar 1, 2026

Evaluation results

MethodLinks
BaseModel=Mistral-7B, Zero-shot=true2026.0365.141.5
BaseModel=Zephyr-7B-β, Zero-shot=true2026.0364.344.8
LLMUModel=Zephyr-7B-β, Zero-shot=true2026.0359.539.5
SSDModel=Zephyr-7B-β, Zero-shot=true2026.0350.235
SCRUBModel=Zephyr-7B-β, Zero-shot=true2026.0343.839.3
ASUModel=Zephyr-7B-β, Zero-shot=true2026.0332.131.7
ASUModel=Mistral-7B, Zero-shot=true2026.0331.529.5
RMUModel=Zephyr-7B-β, Zero-shot=true2026.0331.228.2
RMUModel=Mistral-7B, Zero-shot=true2026.0330.732.3