Noometry

Model comparison

Claude 3 Haiku vs Mistral 7B

Claude 3 Haiku is the stronger model overall, scoring 25.9 to 23.0 on the Noometry Index.

Last verified . 27 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Mistral 7B Mistral AI

23.0

Rank #351 Confirmed

Summary

  • They share 27 benchmarks with published results for both. Claude 3 Haiku scores higher in 7 categories and Mistral 7B in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where Claude 3 Haiku leads 36.0 to 25.8.
  • The biggest single-benchmark swing is BigCodeBench Complete: 50.1% for Claude 3 Haiku and 27.3% for Mistral 7B.
  • Mistral 7B has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuMistral 7B
ProviderAnthropicMistral AI
Noometry Index25.923.0
Released2024-03-072023-09-27
WeightsProprietaryOpen
Context window—8K
Max output—8K
Input $ / M tokens—$0.25
Output $ / M tokens—$0.25
Results tracked3737

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

Category by category

Coding Too close to call

Claude 3 Haiku: 26.4 (#325), Mistral 7B: 26.4 (#326)

BenchmarkClaude 3 HaikuMistral 7B
BigCodeBench Instruct39.4%19.5%
LMArena Coding11991082
BigCodeBench Complete50.1%27.3%
HumanEval+68.9%36%
MBPP+68.8%42.1%
WeirdML9.8%—
CadEval12%—

Reasoning Claude 3 Haiku leads

Claude 3 Haiku: 16.3 (#307), Mistral 7B: 13.1 (#336)

BenchmarkClaude 3 HaikuMistral 7B
LMArena Hard Prompts11741067
DTBench50.1%42.5%
Epoch Capabilities Index118.35112.21
WinoGrande74.2%75.3%
Kagi LLM Benchmark34.2%—
Chess Puzzles—0%
LMCA8.8%—
Adversarial NLI—47.1%
BIG-Bench Hard—56.1%
ForecastBench53.2—
HellaSwag—81%
PIQA—83%

Math Claude 3 Haiku leads

Claude 3 Haiku: 9.8 (#319), Mistral 7B: 8.1 (#325)

BenchmarkClaude 3 HaikuMistral 7B
OTIS Mock AIME 2024-20251.8%0.3%
LMArena Math11881085
MATH Level 514.9%3.7%
GSM8K—54.4%

Knowledge Claude 3 Haiku leads

Claude 3 Haiku: 17.3 (#285), Mistral 7B: 7.4 (#311)

BenchmarkClaude 3 HaikuMistral 7B
GPQA Diamond36.3%15.2%
LMArena Expert11481036
MMLU73.8%62.5%
Confabulations34.2%—
ARC (AI2) Challenge—78.6%
BoolQ—87.4%
OpenBookQA—79.8%
TriviaQA—75.2%

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), Mistral 7B: —

BenchmarkClaude 3 HaikuMistral 7B
LMArena Vision950—
ScienceQA72%—

Multilingual Claude 3 Haiku leads

Claude 3 Haiku: 36.0 (#243), Mistral 7B: 25.8 (#283)

BenchmarkClaude 3 HaikuMistral 7B
LMArena Non-English11781012
LMArena Chinese11551009
LMArena French11951037
LMArena German1174987
LMArena Japanese1102878
LMArena Russian12041018
LMArena Spanish11661026
LMArena Korean1109—

Instruction Following Claude 3 Haiku leads

Claude 3 Haiku: 61.3 (#247), Mistral 7B: 54.2 (#280)

BenchmarkClaude 3 HaikuMistral 7B
LMArena Instruction Following11731060

Long Context Claude 3 Haiku leads

Claude 3 Haiku: 36.1 (#237), Mistral 7B: 32.2 (#271)

BenchmarkClaude 3 HaikuMistral 7B
LMArena Longer Query11901060

Writing & Preference Mistral 7B leads

Claude 3 Haiku: 29.7 (#291), Mistral 7B: 30.7 (#286)

BenchmarkClaude 3 HaikuMistral 7B
LMArena Text11951090
LMArena Creative Writing11571068
LMArena Multi-Turn11901062
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than Mistral 7B?

Claude 3 Haiku is the stronger model overall, scoring 25.9 to 23.0 on the Noometry Index.

Is Claude 3 Haiku or Mistral 7B better for coding?

They score almost the same on coding (26.4 vs 26.4); test both on your own repository before choosing.

How many benchmarks do Claude 3 Haiku and Mistral 7B share?

27 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Mistral 7B has 37.

Related comparisons

Go deeper