Noometry

Model comparison

Claude 3 Haiku vs Mistral Small 3.1

Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 25.9 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Mistral Small 3.1 Mistral AI

31.7

Rank #269 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Mistral Small 3.1 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Mistral Small 3.1 leads 38.3 to 26.4.
  • The biggest single-benchmark swing is GPQA Diamond: 36.3% for Claude 3 Haiku and 41.9% for Mistral Small 3.1.
  • Mistral Small 3.1 has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuMistral Small 3.1
ProviderAnthropicMistral AI
Noometry Index25.931.7
Released2024-03-072025-03-17
WeightsProprietaryOpen
Context window—128K
Max output—102K
Input $ / M tokens—$0.35
Output $ / M tokens—$0.56
Results tracked3728

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

Category by category

Coding Mistral Small 3.1 leads

Claude 3 Haiku: 26.4 (#325), Mistral Small 3.1: 38.3 (#179)

BenchmarkClaude 3 HaikuMistral Small 3.1
LMArena Coding11991309
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Mistral Small 3.1 leads

Claude 3 Haiku: 16.3 (#307), Mistral Small 3.1: 19.7 (#254)

BenchmarkClaude 3 HaikuMistral Small 3.1
LMArena Hard Prompts11741278
Epoch Capabilities Index118.35127.48
Kagi LLM Benchmark34.2%—
Chess Puzzles—1%
DTBench50.1%—
LMCA8.8%—
ForecastBench53.2—
WinoGrande74.2%—

Math Mistral Small 3.1 leads

Claude 3 Haiku: 9.8 (#319), Mistral Small 3.1: 14.7 (#301)

BenchmarkClaude 3 HaikuMistral Small 3.1
OTIS Mock AIME 2024-20251.8%3.9%
LMArena Math11881262
Omni-MATH—24.8%
MATH Level 514.9%—

Knowledge Mistral Small 3.1 leads

Claude 3 Haiku: 17.3 (#285), Mistral Small 3.1: 22.6 (#271)

BenchmarkClaude 3 HaikuMistral Small 3.1
GPQA Diamond36.3%41.9%
LMArena Expert11481257
MMLU-Pro—61%
Confabulations34.2%—
GPQA (HELM)—39.2%
MMLU73.8%—

Multimodal Mistral Small 3.1 leads

Claude 3 Haiku: 23.6 (#128), Mistral Small 3.1: 33.2 (#99)

BenchmarkClaude 3 HaikuMistral Small 3.1
LMArena Vision9501136
ScienceQA72%—

Multilingual Mistral Small 3.1 leads

Claude 3 Haiku: 36.0 (#243), Mistral Small 3.1: 41.2 (#209)

BenchmarkClaude 3 HaikuMistral Small 3.1
LMArena Non-English11781255
LMArena Chinese11551253
LMArena French11951273
LMArena German11741266
LMArena Japanese11021208
LMArena Korean11091206
LMArena Russian12041263
LMArena Spanish11661283

Instruction Following Mistral Small 3.1 leads

Claude 3 Haiku: 61.3 (#247), Mistral Small 3.1: 63.6 (#230)

BenchmarkClaude 3 HaikuMistral Small 3.1
LMArena Instruction Following11731264
IFEval—75%

Long Context Mistral Small 3.1 leads

Claude 3 Haiku: 36.1 (#237), Mistral Small 3.1: 39.5 (#178)

BenchmarkClaude 3 HaikuMistral Small 3.1
LMArena Longer Query11901299

Writing & Preference Mistral Small 3.1 leads

Claude 3 Haiku: 29.7 (#291), Mistral Small 3.1: 37.0 (#259)

BenchmarkClaude 3 HaikuMistral Small 3.1
LMArena Text11951277
LMArena Creative Writing11571253
EQ-Bench Creative Writing717761
LMArena Multi-Turn11901270
WildBench—78.8%

Frequently asked questions

Is Claude 3 Haiku better than Mistral Small 3.1?

Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Mistral Small 3.1 better for coding?

Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Mistral Small 3.1 share?

22 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Mistral Small 3.1 has 28.

Related comparisons

Go deeper