Noometry

Model comparison

Command R vs Gemma 3 12B

Command R and Gemma 3 12B score almost the same on the Noometry Index (31.4 vs 32.1), so choose on price, context window or the category you care about most.

Last verified . 14 shared benchmarks.

Command R Cohere

31.4

Rank #272 Confirmed

Gemma 3 12B Google

32.1

Rank #262 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Command R scores higher in 2 categories and Gemma 3 12B in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in instruction following, where Gemma 3 12B leads 68.6 to 58.1.
  • Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.15 / $0.60 for Command R.
  • Gemma 3 12B accepts more context: 131K tokens versus 128K.

Side by side

Command RGemma 3 12B
ProviderCohereGoogle
Noometry Index31.432.1
Released2024-08-302025-03-12
WeightsOpenOpen
Context window128K131K
Max output4K8K
Input $ / M tokens$0.15$0.05
Output $ / M tokens$0.60$0.15
Results tracked2924

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

Category by category

Coding Gemma 3 12B leads

Command R: 29.3 (#306), Gemma 3 12B: 31.7 (#280)

BenchmarkCommand RGemma 3 12B
LMArena Coding11691281
SciCode—17.4%
BigCodeBench Instruct37.1%—
LiveBench Coding17.9%—
BigCodeBench Complete45.2%—

Agentic & Tool Use Not comparable

Command R: —, Gemma 3 12B: 25.5 (#108)

BenchmarkCommand RGemma 3 12B
Berkeley Function Calling Leaderboard—30.4%

Reasoning Gemma 3 12B leads

Command R: 13.8 (#331), Gemma 3 12B: 15.7 (#313)

BenchmarkCommand RGemma 3 12B
LMArena Hard Prompts11641309
DTBench46.4%48.8%
LMCA9.2%4.5%
CritPt—0%
Chess Puzzles—0%
LiveBench Reasoning21.9%—
LiveBench Data Analysis33.3%—
Epoch Capabilities Index—123.5
LiveBench27.5%—

Math Command R leads

Command R: 28.0 (#246), Gemma 3 12B: 22.3 (#279)

BenchmarkCommand RGemma 3 12B
LMArena Math11551307
OTIS Mock AIME 2024-2025—16.7%
LiveBench Math19.4%—

Knowledge Command R leads

Command R: 31.0 (#221), Gemma 3 12B: 26.5 (#257)

BenchmarkCommand RGemma 3 12B
LMArena Expert11381248
GPQA Diamond—39.5%
Vectara Hallucination Rate—4.4%
MMLU65.2%—

Multimodal Not comparable

Command R: —, Gemma 3 12B: —

BenchmarkCommand RGemma 3 12B
MindCube—46.7%

Multilingual Gemma 3 12B leads

Command R: 35.7 (#245), Gemma 3 12B: 45.7 (#165)

BenchmarkCommand RGemma 3 12B
LMArena Non-English11741318
LMArena German11761370
LMArena Russian11741335
LMArena Chinese1182—
LMArena French1162—
LMArena Japanese1143—
LMArena Korean1163—
LMArena Spanish1151—

Instruction Following Gemma 3 12B leads

Command R: 58.1 (#261), Gemma 3 12B: 68.6 (#186)

BenchmarkCommand RGemma 3 12B
LMArena Instruction Following11671299
LiveBench Instruction Following55.6%—

Long Context Gemma 3 12B leads

Command R: 36.3 (#231), Gemma 3 12B: 40.0 (#162)

BenchmarkCommand RGemma 3 12B
LMArena Longer Query11981317

Writing & Preference Gemma 3 12B leads

Command R: 38.2 (#254), Gemma 3 12B: 47.5 (#209)

BenchmarkCommand RGemma 3 12B
LMArena Text11871334
LMArena Creative Writing11701331
LMArena Multi-Turn11631334
EQ-Bench Creative Writing—1126
LiveBench Language16.7%—

Frequently asked questions

Is Command R better than Gemma 3 12B?

Command R and Gemma 3 12B score almost the same on the Noometry Index (31.4 vs 32.1), so choose on price, context window or the category you care about most.

Which is cheaper, Command R or Gemma 3 12B?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Command R lists at $0.15 and $0.60.

Is Command R or Gemma 3 12B better for coding?

Gemma 3 12B scores higher on coding benchmarks: 31.7 versus 29.3 in the Noometry coding category.

Which has the bigger context window?

Gemma 3 12B does, with 131K tokens against 128K.

How many benchmarks do Command R and Gemma 3 12B share?

14 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Gemma 3 12B has 24.

Related comparisons

Go deeper