Noometry

Model comparison

Claude 3.5 Haiku vs Command R+

Command R+ is the stronger model overall, scoring 32.4 to 29.2 on the Noometry Index.

Last verified . 29 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

Command R+ Cohere

32.4

Rank #257 Confirmed

Summary

  • They share 29 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 5 categories and Command R+ in 3 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Command R+ leads 36.4 to 18.7.
  • The biggest single-benchmark swing is LiveBench Coding: 51.4% for Claude 3.5 Haiku and 19.1% for Command R+.
  • Command R+ has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuCommand R+
ProviderAnthropicCohere
Noometry Index29.232.4
Released2024-10-222024-08-30
WeightsProprietaryOpen
Context window—128K
Max output—4K
Input $ / M tokens—$2.50
Output $ / M tokens—$10
Results tracked4934

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

Category by category

Coding Claude 3.5 Haiku leads

Claude 3.5 Haiku: 32.9 (#265), Command R+: 29.1 (#309)

BenchmarkClaude 3.5 HaikuCommand R+
BigCodeBench Instruct46.1%33.8%
LiveBench Coding51.4%19.1%
LMArena Coding12861187
BigCodeBench Complete59%41.9%
Aider Polyglot28%—
SciCode27.4%—
WeirdML30.7%—
CadEval32%—
HumanEval+—56.7%
MBPP+—63.5%

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 28.0 (#95), Command R+: —

BenchmarkClaude 3.5 HaikuCommand R+
BALROG19.3%—

Reasoning Claude 3.5 Haiku leads

Claude 3.5 Haiku: 17.7 (#290), Command R+: 9.2 (#344)

BenchmarkClaude 3.5 HaikuCommand R+
LiveBench Reasoning28.1%24.8%
LMArena Hard Prompts12511186
DTBench56.7%54.9%
LiveBench Data Analysis48.5%38.1%
Epoch Capabilities Index127.15119.34
LiveBench43.5%31.8%
SimpleBench—17.4%
CritPt0%—
LMCA—5%

Math Command R+ leads

Claude 3.5 Haiku: 14.7 (#300), Command R+: 28.9 (#242)

BenchmarkClaude 3.5 HaikuCommand R+
LiveBench Math35.5%21.3%
LMArena Math12441188
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Command R+ leads

Claude 3.5 Haiku: 18.7 (#281), Command R+: 36.4 (#169)

BenchmarkClaude 3.5 HaikuCommand R+
LMArena Expert12081174
MMLU74.3%69.4%
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
Vectara Hallucination Rate—6.9%
GPQA (HELM)36.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), Command R+: —

BenchmarkClaude 3.5 HaikuCommand R+
LMArena Vision1092—
GeoBench34%—

Multilingual Claude 3.5 Haiku leads

Claude 3.5 Haiku: 40.0 (#218), Command R+: 38.6 (#227)

BenchmarkClaude 3.5 HaikuCommand R+
LMArena Non-English12381216
LMArena Chinese12291226
LMArena French12641209
LMArena German12371216
LMArena Japanese11751166
LMArena Korean11731138
LMArena Russian12531227
LMArena Spanish12611189

Instruction Following Claude 3.5 Haiku leads

Claude 3.5 Haiku: 62.9 (#234), Command R+: 60.0 (#254)

BenchmarkClaude 3.5 HaikuCommand R+
LiveBench Instruction Following61.9%57.6%
LMArena Instruction Following12411197
IFEval79.2%—

Long Context Too close to call

Claude 3.5 Haiku: 38.3 (#200), Command R+: 37.3 (#219)

BenchmarkClaude 3.5 HaikuCommand R+
LMArena Longer Query12611230

Writing & Preference Too close to call

Claude 3.5 Haiku: 42.7 (#234), Command R+: 43.5 (#228)

BenchmarkClaude 3.5 HaikuCommand R+
LMArena Text12551229
LMArena Creative Writing12331235
LMArena Multi-Turn12651213
LiveBench Language35.4%29.7%
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—

Frequently asked questions

Is Claude 3.5 Haiku better than Command R+?

Command R+ is the stronger model overall, scoring 32.4 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or Command R+ better for coding?

Claude 3.5 Haiku scores higher on coding benchmarks: 32.9 versus 29.1 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Command R+ share?

29 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Command R+ has 34.

Related comparisons

Go deeper