Noometry

Model comparison

Claude 3 Haiku vs Command R+

Command R+ is the stronger model overall, scoring 32.4 to 25.9 on the Noometry Index.

Last verified . 25 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Command R+ Cohere

32.4

Rank #257 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude 3 Haiku scores higher in 2 categories and Command R+ in 6 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Command R+ leads 36.4 to 17.3.
  • The biggest single-benchmark swing is BigCodeBench Complete: 50.1% for Claude 3 Haiku and 41.9% for Command R+.
  • Command R+ has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuCommand R+
ProviderAnthropicCohere
Noometry Index25.932.4
Released2024-03-072024-08-30
WeightsProprietaryOpen
Context window—128K
Max output—4K
Input $ / M tokens—$2.50
Output $ / M tokens—$10
Results tracked3734

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

Category by category

Coding Command R+ leads

Claude 3 Haiku: 26.4 (#325), Command R+: 29.1 (#309)

BenchmarkClaude 3 HaikuCommand R+
BigCodeBench Instruct39.4%33.8%
LMArena Coding11991187
BigCodeBench Complete50.1%41.9%
HumanEval+68.9%56.7%
MBPP+68.8%63.5%
WeirdML9.8%—
LiveBench Coding—19.1%
CadEval12%—

Reasoning Claude 3 Haiku leads

Claude 3 Haiku: 16.3 (#307), Command R+: 9.2 (#344)

BenchmarkClaude 3 HaikuCommand R+
LMArena Hard Prompts11741186
DTBench50.1%54.9%
LMCA8.8%5%
Epoch Capabilities Index118.35119.34
SimpleBench—17.4%
Kagi LLM Benchmark34.2%—
LiveBench Reasoning—24.8%
LiveBench Data Analysis—38.1%
ForecastBench53.2—
LiveBench—31.8%
WinoGrande74.2%—

Math Command R+ leads

Claude 3 Haiku: 9.8 (#319), Command R+: 28.9 (#242)

BenchmarkClaude 3 HaikuCommand R+
LMArena Math11881188
OTIS Mock AIME 2024-20251.8%—
LiveBench Math—21.3%
MATH Level 514.9%—

Knowledge Command R+ leads

Claude 3 Haiku: 17.3 (#285), Command R+: 36.4 (#169)

BenchmarkClaude 3 HaikuCommand R+
LMArena Expert11481174
MMLU73.8%69.4%
GPQA Diamond36.3%—
Confabulations34.2%—
Vectara Hallucination Rate—6.9%

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), Command R+: —

BenchmarkClaude 3 HaikuCommand R+
LMArena Vision950—
ScienceQA72%—

Multilingual Command R+ leads

Claude 3 Haiku: 36.0 (#243), Command R+: 38.6 (#227)

BenchmarkClaude 3 HaikuCommand R+
LMArena Non-English11781216
LMArena Chinese11551226
LMArena French11951209
LMArena German11741216
LMArena Japanese11021166
LMArena Korean11091138
LMArena Russian12041227
LMArena Spanish11661189

Instruction Following Claude 3 Haiku leads

Claude 3 Haiku: 61.3 (#247), Command R+: 60.0 (#254)

BenchmarkClaude 3 HaikuCommand R+
LMArena Instruction Following11731197
LiveBench Instruction Following—57.6%

Long Context Command R+ leads

Claude 3 Haiku: 36.1 (#237), Command R+: 37.3 (#219)

BenchmarkClaude 3 HaikuCommand R+
LMArena Longer Query11901230

Writing & Preference Command R+ leads

Claude 3 Haiku: 29.7 (#291), Command R+: 43.5 (#228)

BenchmarkClaude 3 HaikuCommand R+
LMArena Text11951229
LMArena Creative Writing11571235
LMArena Multi-Turn11901213
EQ-Bench Creative Writing717—
LiveBench Language—29.7%

Frequently asked questions

Is Claude 3 Haiku better than Command R+?

Command R+ is the stronger model overall, scoring 32.4 to 25.9 on the Noometry Index.

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

Command R+ scores higher on coding benchmarks: 29.1 versus 26.4 in the Noometry coding category.

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

25 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Command R+ has 34.

Related comparisons

Go deeper