Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Medical Instruction Following on MultiChallenge (Pass@1)

66.8Pass@1

Gemini 3.0 Pro

56.19258.94661.764.454Feb 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
66.8
2026.02
61.9
2026.02
60
2026.02
56.6