The best Google model for reasoning is Gemini 3 Flash Preview — 46.4 intelligence with extended step-by-step thinking. Gemini 3.5 Flash (43.3) and Gemini 3.1 Pro Preview (41.3) round out the top three.
Large language models with extended reasoning / thinking, ranked by intelligence. The best models for complex multi-step reasoning, math and analysis.
The best Google model for reasoning is Gemini 3 Flash Preview — 46.4 intelligence with extended step-by-step thinking. Gemini 3.5 Flash (43.3) and Gemini 3.1 Pro Preview (41.3) round out the top three.
Gemini 3.5 Flash (43.3) is the closest alternative on this metric, followed by Gemini 3.1 Pro Preview (41.3). See the full ranking above for the tradeoffs.
modelgrep tracks 26 Google models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Gemini 3 Flash Preview. 18 of them qualify for this ranking.