Gemini 1.5
Google DeepMind — Gemini
rich detail 13 method fields published
Evaluation
Functional MATH (reasoning gap)
Benchmark derived from MATH with 1,745 original and modified problems; Reasoning Gap metric (relative decrease on modified problems); December snapshot; zero-shot
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.