Noometry

Model comparison

Command R vs Gemma 2 27B

Command R is the stronger model overall, scoring 31.4 to 29.4 on the Noometry Index.

Last verified . 29 shared benchmarks.

Command R Cohere

31.4

Rank #272 Confirmed

Gemma 2 27B Google

29.4

Rank #312 Confirmed

Summary

  • They share 29 benchmarks with published results for both. Command R scores higher in 2 categories and Gemma 2 27B in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Command R leads 28.0 to 10.7.
  • The biggest single-benchmark swing is LiveBench Coding: 17.9% for Command R and 36% for Gemma 2 27B.
  • Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
  • Command R accepts more context: 128K tokens versus 8K.

Side by side

Command RGemma 2 27B
ProviderCohereGoogle
Noometry Index31.429.4
Released2024-08-302024-06-24
WeightsOpenOpen
Context window128K8K
Max output4K2K
Input $ / M tokens$0.15$0.65
Output $ / M tokens$0.60$0.65
Results tracked2934

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

Category by category

Coding Gemma 2 27B leads

Command R: 29.3 (#306), Gemma 2 27B: 34.1 (#246)

BenchmarkCommand RGemma 2 27B
BigCodeBench Instruct37.1%42.8%
LiveBench Coding17.9%36%
LMArena Coding11691211
BigCodeBench Complete45.2%52.5%

Reasoning Gemma 2 27B leads

Command R: 13.8 (#331), Gemma 2 27B: 15.3 (#315)

BenchmarkCommand RGemma 2 27B
LiveBench Reasoning21.9%28.1%
LMArena Hard Prompts11641198
DTBench46.4%48%
LiveBench Data Analysis33.3%47.9%
LMCA9.2%7.1%
LiveBench27.5%38.2%
Epoch Capabilities Index—122.08

Math Command R leads

Command R: 28.0 (#246), Gemma 2 27B: 10.7 (#311)

BenchmarkCommand RGemma 2 27B
LiveBench Math19.4%26.5%
LMArena Math11551212
OTIS Mock AIME 2024-2025—1.4%
MATH Level 5—27.9%

Knowledge Command R leads

Command R: 31.0 (#221), Gemma 2 27B: 19.0 (#280)

BenchmarkCommand RGemma 2 27B
LMArena Expert11381172
MMLU65.2%75.7%
GPQA Diamond—36.5%
Confabulations—27.1%

Multilingual Gemma 2 27B leads

Command R: 35.7 (#245), Gemma 2 27B: 38.6 (#226)

BenchmarkCommand RGemma 2 27B
LMArena Non-English11741217
LMArena Chinese11821221
LMArena French11621247
LMArena German11761209
LMArena Japanese11431175
LMArena Korean11631174
LMArena Russian11741234
LMArena Spanish11511228

Instruction Following Gemma 2 27B leads

Command R: 58.1 (#261), Gemma 2 27B: 60.5 (#249)

BenchmarkCommand RGemma 2 27B
LiveBench Instruction Following55.6%58.1%
LMArena Instruction Following11671206

Long Context Gemma 2 27B leads

Command R: 36.3 (#231), Gemma 2 27B: 37.3 (#218)

BenchmarkCommand RGemma 2 27B
LMArena Longer Query11981231

Writing & Preference Gemma 2 27B leads

Command R: 38.2 (#254), Gemma 2 27B: 44.2 (#225)

BenchmarkCommand RGemma 2 27B
LMArena Text11871231
LMArena Creative Writing11701241
LMArena Multi-Turn11631224
LiveBench Language16.7%32.6%

Frequently asked questions

Is Command R better than Gemma 2 27B?

Command R is the stronger model overall, scoring 31.4 to 29.4 on the Noometry Index.

Which is cheaper, Command R or Gemma 2 27B?

Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.

Is Command R or Gemma 2 27B better for coding?

Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 29.3 in the Noometry coding category.

Which has the bigger context window?

Command R does, with 128K tokens against 8K.

How many benchmarks do Command R and Gemma 2 27B share?

29 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Gemma 2 27B has 34.

Related comparisons

Go deeper