Noometry

Model comparison

Claude 3 Haiku vs Magistral Small

Magistral Small is the stronger model overall, scoring 30.2 to 25.9 on the Noometry Index.

Last verified . 5 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Magistral Small Mistral AI

30.2

Rank #296 Confirmed

Summary

  • They share 5 benchmarks with published results for both. Claude 3 Haiku scores higher in 1 category and Magistral Small in 3 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where Magistral Small leads 26.2 to 9.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 30% for Magistral Small.
  • Magistral Small has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuMagistral Small
ProviderAnthropicMistral AI
Noometry Index25.930.2
Released2024-03-072025-06-10
WeightsProprietaryOpen
Context window—128K
Max output—40K
Input $ / M tokens—$0.50
Output $ / M tokens—$1.50
Results tracked3710

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

Category by category

Coding Magistral Small leads

Claude 3 Haiku: 26.4 (#325), Magistral Small: 38.4 (#176)

BenchmarkClaude 3 HaikuMagistral Small
SciCode—35.2%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
LMArena Coding1199—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Claude 3 Haiku leads

Claude 3 Haiku: 16.3 (#307), Magistral Small: 6.8 (#350)

BenchmarkClaude 3 HaikuMagistral Small
Kagi LLM Benchmark34.2%6.3%
DTBench50.1%61.3%
Epoch Capabilities Index118.35133.19
ARC-AGI-2—0%
ARC-AGI-1—5%
CritPt—0.3%
Chess Puzzles—3%
LMArena Hard Prompts1174—
LMCA8.8%—
ForecastBench53.2—
WinoGrande74.2%—

Math Magistral Small leads

Claude 3 Haiku: 9.8 (#319), Magistral Small: 26.2 (#261)

BenchmarkClaude 3 HaikuMagistral Small
OTIS Mock AIME 2024-20251.8%30%
LMArena Math1188—
MATH Level 514.9%—

Knowledge Magistral Small leads

Claude 3 Haiku: 17.3 (#285), Magistral Small: 30.9 (#223)

BenchmarkClaude 3 HaikuMagistral Small
GPQA Diamond36.3%56.1%
Confabulations34.2%—
LMArena Expert1148—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), Magistral Small: —

BenchmarkClaude 3 HaikuMagistral Small
LMArena Vision950—
ScienceQA72%—

Multilingual Not comparable

Claude 3 Haiku: 36.0 (#243), Magistral Small: —

BenchmarkClaude 3 HaikuMagistral Small
LMArena Non-English1178—
LMArena Chinese1155—
LMArena French1195—
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1109—
LMArena Russian1204—
LMArena Spanish1166—

Instruction Following Not comparable

Claude 3 Haiku: 61.3 (#247), Magistral Small: —

BenchmarkClaude 3 HaikuMagistral Small
LMArena Instruction Following1173—

Long Context Not comparable

Claude 3 Haiku: 36.1 (#237), Magistral Small: —

BenchmarkClaude 3 HaikuMagistral Small
LMArena Longer Query1190—

Writing & Preference Not comparable

Claude 3 Haiku: 29.7 (#291), Magistral Small: —

BenchmarkClaude 3 HaikuMagistral Small
LMArena Text1195—
LMArena Creative Writing1157—
EQ-Bench Creative Writing717—
LMArena Multi-Turn1190—

Frequently asked questions

Is Claude 3 Haiku better than Magistral Small?

Magistral Small is the stronger model overall, scoring 30.2 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Magistral Small better for coding?

Magistral Small scores higher on coding benchmarks: 38.4 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Magistral Small share?

5 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Magistral Small has 10.

Related comparisons

Go deeper