Noometry

Model comparison

Command A vs Gemma 3 12B

Command A is the stronger model overall, scoring 36.5 to 32.1 on the Noometry Index. Gemma 3 12B costs 58× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.

Last verified . 17 shared benchmarks.

Command A Cohere

36.5

Rank #215 Confirmed

Gemma 3 12B Google

32.1

Rank #262 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Command A scores higher in 7 categories and Gemma 3 12B in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Command A leads 36.2 to 22.3.
  • The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 57.1% for Command A and 30.4% for Gemma 3 12B.
  • Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $2.50 / $10 for Command A.
  • Command A accepts more context: 256K tokens versus 131K.

Side by side

Command AGemma 3 12B
ProviderCohereGoogle
Noometry Index36.532.1
Released2025-03-132025-03-12
WeightsOpenOpen
Context window256K131K
Max output8K8K
Input $ / M tokens$2.50$0.05
Output $ / M tokens$10$0.15
Results tracked2424

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

Category by category

Coding Gemma 3 12B leads

Command A: 27.2 (#322), Gemma 3 12B: 31.7 (#280)

BenchmarkCommand AGemma 3 12B
LMArena Coding13301281
Aider Polyglot12%—
SciCode—17.4%

Agentic & Tool Use Command A leads

Command A: 35.9 (#40), Gemma 3 12B: 25.5 (#108)

BenchmarkCommand AGemma 3 12B
Berkeley Function Calling Leaderboard57.1%30.4%

Reasoning Command A leads

Command A: 18.3 (#283), Gemma 3 12B: 15.7 (#313)

BenchmarkCommand AGemma 3 12B
LMArena Hard Prompts13261309
DTBench61.3%48.8%
LMCA10.3%4.5%
Kagi LLM Benchmark28.8%—
CritPt—0%
Chess Puzzles—0%
Epoch Capabilities Index—123.5

Math Command A leads

Command A: 36.2 (#171), Gemma 3 12B: 22.3 (#279)

BenchmarkCommand AGemma 3 12B
LMArena Math13001307
OTIS Mock AIME 2024-2025—16.7%

Knowledge Command A leads

Command A: 37.1 (#159), Gemma 3 12B: 26.5 (#257)

BenchmarkCommand AGemma 3 12B
Vectara Hallucination Rate9.3%4.4%
LMArena Expert12951248
GPQA Diamond—39.5%

Multimodal Not comparable

Command A: —, Gemma 3 12B: —

BenchmarkCommand AGemma 3 12B
MindCube—46.7%

Multilingual Too close to call

Command A: 45.3 (#170), Gemma 3 12B: 45.7 (#165)

BenchmarkCommand AGemma 3 12B
LMArena Non-English13131318
LMArena German13411370
LMArena Russian13141335
LMArena Chinese1327—
LMArena French1351—
LMArena Japanese1285—
LMArena Korean1285—
LMArena Spanish1347—

Instruction Following Too close to call

Command A: 69.1 (#177), Gemma 3 12B: 68.6 (#186)

BenchmarkCommand AGemma 3 12B
LMArena Instruction Following13091299

Long Context Too close to call

Command A: 40.6 (#151), Gemma 3 12B: 40.0 (#162)

BenchmarkCommand AGemma 3 12B
LMArena Longer Query13341317

Writing & Preference Too close to call

Command A: 47.6 (#208), Gemma 3 12B: 47.5 (#209)

BenchmarkCommand AGemma 3 12B
LMArena Text13311334
LMArena Creative Writing13191331
EQ-Bench Creative Writing11451126
LMArena Multi-Turn13391334

Frequently asked questions

Is Command A better than Gemma 3 12B?

Command A is the stronger model overall, scoring 36.5 to 32.1 on the Noometry Index. Gemma 3 12B costs 58× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.

Which is cheaper, Command A 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 A lists at $2.50 and $10.

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

Gemma 3 12B scores higher on coding benchmarks: 31.7 versus 27.2 in the Noometry coding category.

Which has the bigger context window?

Command A does, with 256K tokens against 131K.

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

17 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Gemma 3 12B has 24.

Related comparisons

Go deeper