BenchLeader
Menu
LeaderboardsModelsProvidersBenchmarksCompareReleasesBlogMethodology
GoogleAuto-detected

Gemini 3 Deep

Not yet ranked: too few independent results so far. Released 12 Feb 2026.

Blended price
–
Output speed
–
First answer
–
Context
–
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Reasoning57

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

BenchmarkthinkingSource
ARC-AGI-187.5%#59ARC Prize
ARC-AGI-245.1%#76ARC Prize

See also

All Google models

Data as of 9 Sept 2026. Compare with another model.