Gemini 2.5
Google DeepMind — Gemini
rich detail 11 method fields published
Evaluation
Close-ended knowledge-based and reasoning MCQs for biology and chemistry, reported on external benchmarks: SecureBio VMQA, FutureHouse LAB-Bench (ProtocolQA, Cloning Scenarios, SeqQA), WMDP (biology, chemistry); answer choices shuffled over 100 runs, mean solve rate
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.
rich detail 11 method fields published