BenchLeader
Deep CogitoAuto-detected

Cogito v2.1

Not yet ranked: too few independent results so far. Released 19 Nov 2025.

Blended price
Output speed
First answer
Context
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Coding45

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.

Coding

BenchmarkdefaultSource
SciCode41.0%#101SciCode

See also

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