Noometry

Model comparison

Command R vs Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 31.4 on the Noometry Index. Command R costs 17× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Last verified . 19 shared benchmarks.

Command R Cohere

31.4

Rank #272 Confirmed

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Command R scores higher in 0 categories and Gemini 3.1 Pro Preview in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 13.8.
  • The biggest single-benchmark swing is DTBench: 46.4% for Command R and 97.1% for Gemini 3.1 Pro Preview.
  • Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 128K.
  • Command R has downloadable open weights; the other is API-only.

Side by side

Command RGemini 3.1 Pro Preview
ProviderCohereGoogle
Noometry Index31.456.7
Released2024-08-302026-02-19
WeightsOpenProprietary
Context window128K1.05M
Max output4K66K
Input $ / M tokens$0.15$2
Output $ / M tokens$0.60$12
Results tracked2971

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

Category by category

Coding Gemini 3.1 Pro Preview leads

Command R: 29.3 (#306), Gemini 3.1 Pro Preview: 42.5 (#99)

BenchmarkCommand RGemini 3.1 Pro Preview
LMArena Coding11691484
SWE-bench Verified—75.6%
DeepSWE—11.7%
LMArena WebDev—1447
SciCode—58.9%
GSO—22.6%
WeirdML—72.1%
BigCodeBench Instruct37.1%—
LiveBench Coding17.9%—
MirrorCode—8.9%
BigCodeBench Complete45.2%—
ALE-Bench—1,161
AlgoTune—2.02

Agentic & Tool Use Not comparable

Command R: —, Gemini 3.1 Pro Preview: 37.7 (#34)

BenchmarkCommand RGemini 3.1 Pro Preview
Terminal-Bench—80.2%
APEX-Agents—35.3%
τ²-bench Banking—26%
DeepResearch Bench—47.8%
PostTrainBench—22%
BALROG—57%
ExploitBench—26.1%
GBAEval—0.8%
GDP.pdf—17%
LMArena Search—1211
METR Time Horizons—77%
Vending-Bench 2—3,774

Reasoning Gemini 3.1 Pro Preview leads

Command R: 13.8 (#331), Gemini 3.1 Pro Preview: 71.7 (#12)

BenchmarkCommand RGemini 3.1 Pro Preview
LMArena Hard Prompts11641485
DTBench46.4%97.1%
LMCA9.2%53.8%
ARC-AGI-2—77.1%
SimpleBench—79.6%
NYT Connections (extended)—97.4%
ARC-AGI-1—98%
CritPt—17.7%
Chess Puzzles—55%
EnigmaEval—36.8%
Thematic Generalization—79.4%
EBR-Bench—14.3%
LiveBench Reasoning21.9%—
Mystery Game Puzzles—34%
LiveBench Data Analysis33.3%—
Epoch Capabilities Index—154.77
ForecastBench—59
LiveBench27.5%—

Math Gemini 3.1 Pro Preview leads

Command R: 28.0 (#246), Gemini 3.1 Pro Preview: 62.1 (#34)

BenchmarkCommand RGemini 3.1 Pro Preview
LMArena Math11551485
FrontierMath (Tiers 1-3)—59.6%
FrontierMath Tier 4—26.8%
MathArena Final-Answer Competitions—86.5%
OTIS Mock AIME 2024-2025—95.6%
ProofBench—26%
LiveBench Math19.4%—
FrontierMath (Feb 2025 set)—36.9%
FrontierMath Tier 4 (v1)—16.7%

Knowledge Gemini 3.1 Pro Preview leads

Command R: 31.0 (#221), Gemini 3.1 Pro Preview: 71.8 (#3)

BenchmarkCommand RGemini 3.1 Pro Preview
LMArena Expert11381485
GPQA Diamond—94.4%
Humanity's Last Exam—46.4%
SimpleQA Verified—73.5%
Vectara Hallucination Rate—10.4%
MMLU65.2%—

Multimodal Not comparable

Command R: —, Gemini 3.1 Pro Preview: 37.9 (#69)

BenchmarkCommand RGemini 3.1 Pro Preview
LMArena Vision—1296
Blueprint-Bench 2—26.5%
Furniture Assembly—26.7%
LMArena Document—1444

Multilingual Gemini 3.1 Pro Preview leads

Command R: 35.7 (#245), Gemini 3.1 Pro Preview: 57.0 (#12)

BenchmarkCommand RGemini 3.1 Pro Preview
LMArena Non-English11741477
LMArena Chinese11821529
LMArena French11621487
LMArena German11761491
LMArena Japanese11431493
LMArena Korean11631455
LMArena Russian11741498
LMArena Spanish11511479

Instruction Following Gemini 3.1 Pro Preview leads

Command R: 58.1 (#261), Gemini 3.1 Pro Preview: 77.0 (#32)

BenchmarkCommand RGemini 3.1 Pro Preview
LMArena Instruction Following11671466
LiveBench Instruction Following55.6%—

Long Context Gemini 3.1 Pro Preview leads

Command R: 36.3 (#231), Gemini 3.1 Pro Preview: 47.4 (#18)

BenchmarkCommand RGemini 3.1 Pro Preview
LMArena Longer Query11981483
CL-bench—20.8%
CL-bench Life—16.9%

Writing & Preference Gemini 3.1 Pro Preview leads

Command R: 38.2 (#254), Gemini 3.1 Pro Preview: 66.1 (#37)

BenchmarkCommand RGemini 3.1 Pro Preview
LMArena Text11871481
LMArena Creative Writing11701482
LMArena Multi-Turn11631488
EQ-Bench Creative Writing—1491
EQ-Bench 4—1142
LiveBench Language16.7%—

Frequently asked questions

Is Command R better than Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 31.4 on the Noometry Index. Command R costs 17× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Which is cheaper, Command R or Gemini 3.1 Pro Preview?

Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Command R or Gemini 3.1 Pro Preview better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 29.3 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 128K.

How many benchmarks do Command R and Gemini 3.1 Pro Preview share?

19 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Gemini 3.1 Pro Preview has 71.

Related comparisons

Go deeper