Noometry

Model comparison

Claude 3.5 Haiku vs Command A

Command A is the stronger model overall, scoring 36.5 to 29.2 on the Noometry Index.

Last verified . 20 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

Command A Cohere

36.5

Rank #215 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 1 category and Command A in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Command A leads 36.2 to 14.7.
  • The biggest single-benchmark swing is Aider Polyglot: 28% for Claude 3.5 Haiku and 12% for Command A.
  • Command A has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuCommand A
ProviderAnthropicCohere
Noometry Index29.236.5
Released2024-10-222025-03-13
WeightsProprietaryOpen
Context window—256K
Max output—8K
Input $ / M tokens—$2.50
Output $ / M tokens—$10
Results tracked4924

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 A: 27.2 (#322)

BenchmarkClaude 3.5 HaikuCommand A
Aider Polyglot28%12%
LMArena Coding12861330
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Command A leads

Claude 3.5 Haiku: 28.0 (#95), Command A: 35.9 (#40)

BenchmarkClaude 3.5 HaikuCommand A
Berkeley Function Calling Leaderboard—57.1%
BALROG19.3%—

Reasoning Too close to call

Claude 3.5 Haiku: 17.7 (#290), Command A: 18.3 (#283)

BenchmarkClaude 3.5 HaikuCommand A
LMArena Hard Prompts12511326
DTBench56.7%61.3%
Kagi LLM Benchmark—28.8%
CritPt0%—
LiveBench Reasoning28.1%—
LiveBench Data Analysis48.5%—
LMCA—10.3%
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math Command A leads

Claude 3.5 Haiku: 14.7 (#300), Command A: 36.2 (#171)

BenchmarkClaude 3.5 HaikuCommand A
LMArena Math12441300
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Command A leads

Claude 3.5 Haiku: 18.7 (#281), Command A: 37.1 (#159)

BenchmarkClaude 3.5 HaikuCommand A
LMArena Expert12081295
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
Vectara Hallucination Rate—9.3%
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Not comparable

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

BenchmarkClaude 3.5 HaikuCommand A
LMArena Vision1092—
GeoBench34%—

Multilingual Command A leads

Claude 3.5 Haiku: 40.0 (#218), Command A: 45.3 (#170)

BenchmarkClaude 3.5 HaikuCommand A
LMArena Non-English12381313
LMArena Chinese12291327
LMArena French12641351
LMArena German12371341
LMArena Japanese11751285
LMArena Korean11731285
LMArena Russian12531314
LMArena Spanish12611347

Instruction Following Command A leads

Claude 3.5 Haiku: 62.9 (#234), Command A: 69.1 (#177)

BenchmarkClaude 3.5 HaikuCommand A
LMArena Instruction Following12411309
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context Command A leads

Claude 3.5 Haiku: 38.3 (#200), Command A: 40.6 (#151)

BenchmarkClaude 3.5 HaikuCommand A
LMArena Longer Query12611334

Writing & Preference Command A leads

Claude 3.5 Haiku: 42.7 (#234), Command A: 47.6 (#208)

BenchmarkClaude 3.5 HaikuCommand A
LMArena Text12551331
LMArena Creative Writing12331319
EQ-Bench Creative Writing11461145
LMArena Multi-Turn12651339
Short-Story Creative Writing73.5%—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Command A?

Command A is the stronger model overall, scoring 36.5 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or Command A better for coding?

Claude 3.5 Haiku scores higher on coding benchmarks: 32.9 versus 27.2 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Command A share?

20 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Command A has 24.

Related comparisons

Go deeper