Noometry

Model comparison

Claude 3 Sonnet vs Command R+

Command R+ is the stronger model overall, scoring 32.0 to 28.8 on the Noometry Index.

Last verified . 24 shared benchmarks.

Claude 3 Sonnet Anthropic

28.8

Rank #311 Confirmed

Command R+ Cohere

32.0

Rank #251 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude 3 Sonnet scores higher in 3 categories and Command R+ in 5 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Command R+ leads 26.6 to 10.0.
  • The biggest single-benchmark swing is BigCodeBench Complete: 53.8% for Claude 3 Sonnet and 41.9% for Command R+.
  • Command R+ has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetCommand R+
ProviderAnthropicCohere
Noometry Index28.832.0
Released2024-02-292024-08-30
WeightsProprietaryOpen
Context window—128K
Max output—4K
Input $ / M tokens—$2.50
Output $ / M tokens—$10
Results tracked3034

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

Category by category

Coding Too close to call

Claude 3 Sonnet: 29.2 (#296), Command R+: 28.6 (#304)

BenchmarkClaude 3 SonnetCommand R+
BigCodeBench Instruct42.7%33.8%
LMArena Coding12231187
BigCodeBench Complete53.8%41.9%
HumanEval+64%56.7%
MBPP+69.3%63.5%
WeirdML10.2%—
LiveBench Coding—19.1%

Reasoning Claude 3 Sonnet leads

Claude 3 Sonnet: 19.7 (#232), Command R+: 8.9 (#341)

BenchmarkClaude 3 SonnetCommand R+
LMArena Hard Prompts11971186
DTBench53.6%54.9%
Epoch Capabilities Index120.69119.28
SimpleBench—17.4%
LiveBench Reasoning—24.8%
LiveBench Data Analysis—38.1%
LMCA—5%
LiveBench—31.8%
WinoGrande75.1%—

Math Command R+ leads

Claude 3 Sonnet: 10.0 (#305), Command R+: 26.6 (#239)

BenchmarkClaude 3 SonnetCommand R+
LMArena Math12131188
OTIS Mock AIME 2024-20252.5%—
LiveBench Math—21.3%
MATH Level 518.2%—

Knowledge Command R+ leads

Claude 3 Sonnet: 21.1 (#271), Command R+: 35.9 (#165)

BenchmarkClaude 3 SonnetCommand R+
LMArena Expert11731174
MMLU75.9%69.4%
GPQA Diamond40.6%—
Vectara Hallucination Rate—6.9%

Multimodal Not comparable

Claude 3 Sonnet: 24.7 (#120), Command R+: —

BenchmarkClaude 3 SonnetCommand R+
LMArena Vision984—

Multilingual Too close to call

Claude 3 Sonnet: 38.0 (#229), Command R+: 38.8 (#222)

BenchmarkClaude 3 SonnetCommand R+
LMArena Non-English12051216
LMArena Chinese11881226
LMArena French12281208
LMArena German12041216
LMArena Japanese11311166
LMArena Korean11281138
LMArena Russian12271227
LMArena Spanish12041189

Instruction Following Claude 3 Sonnet leads

Claude 3 Sonnet: 63.1 (#230), Command R+: 60.2 (#249)

BenchmarkClaude 3 SonnetCommand R+
LMArena Instruction Following12001197
LiveBench Instruction Following—57.6%

Long Context Too close to call

Claude 3 Sonnet: 36.7 (#223), Command R+: 37.3 (#214)

BenchmarkClaude 3 SonnetCommand R+
LMArena Longer Query12111231

Writing & Preference Command R+ leads

Claude 3 Sonnet: 42.3 (#233), Command R+: 43.7 (#223)

BenchmarkClaude 3 SonnetCommand R+
LMArena Text12181229
LMArena Creative Writing11861235
LMArena Multi-Turn12271213
LiveBench Language—29.7%

Frequently asked questions

Is Claude 3 Sonnet better than Command R+?

Command R+ is the stronger model overall, scoring 32.0 to 28.8 on the Noometry Index.

Is Claude 3 Sonnet or Command R+ better for coding?

They score almost the same on coding (29.2 vs 28.6); test both on your own repository before choosing.

How many benchmarks do Claude 3 Sonnet and Command R+ share?

24 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Command R+ has 34.

Related comparisons

Go deeper