Noometry

Model comparison

Command R+ vs Grok-3 mini

Grok-3 mini is the stronger model overall, scoring 41.2 to 32.4 on the Noometry Index.

Last verified . 18 shared benchmarks.

Command R+ Cohere

32.4

Rank #257 Confirmed

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Command R+ scores higher in 0 categories and Grok-3 mini in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in instruction following, where Grok-3 mini leads 78.5 to 60.0.
  • Command R+ has downloadable open weights; the other is API-only.

Side by side

Command R+Grok-3 mini
ProviderCoherexAI
Noometry Index32.441.2
Released2024-08-302025-04-09
WeightsOpenProprietary
Context window128K—
Max output4K—
Input $ / M tokens$2.50—
Output $ / M tokens$10—
Results tracked3435

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Grok-3 mini leads

Command R+: 29.1 (#309), Grok-3 mini: 40.8 (#131)

BenchmarkCommand R+Grok-3 mini
LMArena Coding11871379
Aider Polyglot—49.3%
WeirdML—42.6%
BigCodeBench Instruct33.8%—
LiveBench Coding19.1%—
BigCodeBench Complete41.9%—
HumanEval+56.7%—
MBPP+63.5%—

Reasoning Grok-3 mini leads

Command R+: 9.2 (#344), Grok-3 mini: 13.6 (#334)

BenchmarkCommand R+Grok-3 mini
LMArena Hard Prompts11861375
Epoch Capabilities Index119.34140.35
ARC-AGI-2—0.4%
SimpleBench17.4%—
Kagi LLM Benchmark—61.3%
ARC-AGI-1—16.5%
LiveBench Reasoning24.8%—
DTBench54.9%—
LiveBench Data Analysis38.1%—
LMCA5%—
LiveBench31.8%—

Math Grok-3 mini leads

Command R+: 28.9 (#242), Grok-3 mini: 42.1 (#85)

BenchmarkCommand R+Grok-3 mini
LMArena Math11881386
OTIS Mock AIME 2024-2025—77.8%
Omni-MATH—31.8%
LiveBench Math21.3%—
MATH Level 5—90.9%
FrontierMath (Feb 2025 set)—5.9%

Knowledge Grok-3 mini leads

Command R+: 36.4 (#169), Grok-3 mini: 46.4 (#81)

BenchmarkCommand R+Grok-3 mini
LMArena Expert11741395
GPQA Diamond—76.3%
MMLU-Pro—79.9%
Confabulations—10.8%
Vectara Hallucination Rate6.9%—
GPQA (HELM)—67.5%
MMLU69.4%—

Multilingual Grok-3 mini leads

Command R+: 38.6 (#227), Grok-3 mini: 48.1 (#145)

BenchmarkCommand R+Grok-3 mini
LMArena Non-English12161352
LMArena Chinese12261387
LMArena French12091357
LMArena German12161349
LMArena Japanese11661342
LMArena Korean11381335
LMArena Russian12271353
LMArena Spanish11891381

Instruction Following Grok-3 mini leads

Command R+: 60.0 (#254), Grok-3 mini: 78.5 (#9)

BenchmarkCommand R+Grok-3 mini
LMArena Instruction Following11971357
LiveBench Instruction Following57.6%—
IFEval—95.1%

Long Context Grok-3 mini leads

Command R+: 37.3 (#219), Grok-3 mini: 41.0 (#147)

BenchmarkCommand R+Grok-3 mini
LMArena Longer Query12301372
Fiction.LiveBench—66.7%

Writing & Preference Grok-3 mini leads

Command R+: 43.5 (#228), Grok-3 mini: 52.5 (#169)

BenchmarkCommand R+Grok-3 mini
LMArena Text12291370
LMArena Creative Writing12351342
LMArena Multi-Turn12131355
Short-Story Creative Writing—73.5%
WildBench—65.1%
LiveBench Language29.7%—

Frequently asked questions

Is Command R+ better than Grok-3 mini?

Grok-3 mini is the stronger model overall, scoring 41.2 to 32.4 on the Noometry Index.

Is Command R+ or Grok-3 mini better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 29.1 in the Noometry coding category.

How many benchmarks do Command R+ and Grok-3 mini share?

18 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Grok-3 mini has 35.

Related comparisons

Go deeper