BenchLeader
Menu
LeaderboardsModelsProvidersBenchmarksCompareReleasesBlogMethodology
CohereAuto-detected

Command R

Best configuration ranks #562 of 610 on the BenchLeader Index at 37.3 ±10.8. Last measured 2 Sept 2026.

Blended price
–
Output speed
–
First answer
–
Context
128k
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index37
  2. Reasoning35
  3. Coding35
  4. Knowledge5
  5. Human preference37
  6. Composite35

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

BenchmarkdefaultSource
LMArena Hard Prompts1214#287LMArena
GPQA Diamond (AA)not in index28.4%#498Artificial Analysis
Humanity's Last Exam (AA)not in index4.8%#396Artificial Analysis

Coding

BenchmarkdefaultSource
LMArena Coding1243#285LMArena

Knowledge

BenchmarkdefaultSource
LegalBench33.0%#136Vals AI

Human preference

BenchmarkdefaultSource
LMArena Text1226#275LMArena

Composite

BenchmarkdefaultSource
AA Intelligence Index5.0#517Artificial Analysis

See also

All Cohere models

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