Noometry

Model comparison

Command R vs Command R+

Command R and Command R+ score almost the same on the Noometry Index (31.0 vs 32.0), so choose on price, context window or the category you care about most.

Last verified . 29 shared benchmarks.

Command R Cohere

31.0

Rank #267 Confirmed

Command R+ Cohere

32.0

Rank #251 Confirmed

Summary

  • They share 29 benchmarks with published results for both. Command R scores higher in 2 categories and Command R+ in 6 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Command R+ leads 35.9 to 30.5.
  • The biggest single-benchmark swing is LiveBench Language: 16.7% for Command R and 29.7% for Command R+.
  • Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $2.50 / $10 for Command R+.

Side by side

Command RCommand R+
ProviderCohereCohere
Noometry Index31.032.0
Released2024-08-302024-08-30
WeightsOpenOpen
Context window128K128K
Max output4K4K
Input $ / M tokens$0.15$2.50
Output $ / M tokens$0.60$10
Results tracked2934

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

Category by category

Coding Too close to call

Command R: 28.8 (#301), Command R+: 28.6 (#304)

BenchmarkCommand RCommand R+
BigCodeBench Instruct37.1%33.8%
LiveBench Coding17.9%19.1%
LMArena Coding11701187
BigCodeBench Complete45.2%41.9%
HumanEval+—56.7%
MBPP+—63.5%

Reasoning Command R leads

Command R: 13.3 (#329), Command R+: 8.9 (#341)

BenchmarkCommand RCommand R+
LiveBench Reasoning21.9%24.8%
LMArena Hard Prompts11641186
DTBench46.4%54.9%
LiveBench Data Analysis33.3%38.1%
LMCA9.2%5%
LiveBench27.5%31.8%
SimpleBench—17.4%
Epoch Capabilities Index—119.28

Math Too close to call

Command R: 25.8 (#244), Command R+: 26.6 (#239)

BenchmarkCommand RCommand R+
LiveBench Math19.4%21.3%
LMArena Math11551188

Knowledge Command R+ leads

Command R: 30.5 (#219), Command R+: 35.9 (#165)

BenchmarkCommand RCommand R+
LMArena Expert11381174
MMLU65.2%69.4%
Vectara Hallucination Rate—6.9%

Multilingual Command R+ leads

Command R: 35.9 (#240), Command R+: 38.8 (#222)

BenchmarkCommand RCommand R+
LMArena Non-English11741216
LMArena Chinese11821226
LMArena French11611208
LMArena German11761216
LMArena Japanese11431166
LMArena Korean11621138
LMArena Russian11741227
LMArena Spanish11501189

Instruction Following Command R+ leads

Command R: 58.3 (#256), Command R+: 60.2 (#249)

BenchmarkCommand RCommand R+
LiveBench Instruction Following55.6%57.6%
LMArena Instruction Following11671197

Long Context Command R+ leads

Command R: 36.3 (#226), Command R+: 37.3 (#214)

BenchmarkCommand RCommand R+
LMArena Longer Query11981231

Writing & Preference Command R+ leads

Command R: 38.4 (#248), Command R+: 43.7 (#223)

BenchmarkCommand RCommand R+
LMArena Text11871229
LMArena Creative Writing11701235
LMArena Multi-Turn11631213
LiveBench Language16.7%29.7%

Frequently asked questions

Is Command R better than Command R+?

Command R and Command R+ score almost the same on the Noometry Index (31.0 vs 32.0), so choose on price, context window or the category you care about most.

Which is cheaper, Command R or Command R+?

Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Command R+ lists at $2.50 and $10.

Is Command R or Command R+ better for coding?

They score almost the same on coding (28.8 vs 28.6); test both on your own repository before choosing.

Which has the bigger context window?

Both accept 128K tokens.

How many benchmarks do Command R and Command R+ share?

29 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Command R+ has 34.

Related comparisons

Go deeper