Noometry

Model comparison

Claude 3 Haiku vs Mixtral 8x22B

Mixtral 8x22B is the stronger model overall, scoring 27.1 to 25.9 on the Noometry Index.

Last verified . 28 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Mixtral 8x22B Mistral AI

27.1

Rank #333 Confirmed

Summary

  • They share 28 benchmarks with published results for both. Claude 3 Haiku scores higher in 5 categories and Mixtral 8x22B in 3 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Mixtral 8x22B leads 22.9 to 9.8.
  • The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku and 24.2% for Mixtral 8x22B.
  • Mixtral 8x22B has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuMixtral 8x22B
ProviderAnthropicMistral AI
Noometry Index25.927.1
Released2024-03-072024-04-17
WeightsProprietaryOpen
Context window—64K
Max output—64K
Input $ / M tokens—$2
Output $ / M tokens—$6
Results tracked3734

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

Category by category

Coding Claude 3 Haiku leads

Claude 3 Haiku: 26.4 (#325), Mixtral 8x22B: 24.2 (#329)

BenchmarkClaude 3 HaikuMixtral 8x22B
WeirdML9.8%3.2%
BigCodeBench Instruct39.4%40.6%
LMArena Coding11991166
BigCodeBench Complete50.1%50.2%
HumanEval+68.9%72%
MBPP+68.8%64.3%
CadEval12%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Mixtral 8x22B: 23.1 (#127)

BenchmarkClaude 3 HaikuMixtral 8x22B
Cybench—7.5%

Reasoning Mixtral 8x22B leads

Claude 3 Haiku: 16.3 (#307), Mixtral 8x22B: 19.9 (#248)

BenchmarkClaude 3 HaikuMixtral 8x22B
LMArena Hard Prompts11741150
DTBench50.1%55.1%
Epoch Capabilities Index118.35122.03
ForecastBench53.256.3
Kagi LLM Benchmark34.2%—
LMCA8.8%—
WinoGrande74.2%—

Math Mixtral 8x22B leads

Claude 3 Haiku: 9.8 (#319), Mixtral 8x22B: 22.9 (#275)

BenchmarkClaude 3 HaikuMixtral 8x22B
LMArena Math11881184
MATH Level 514.9%24.2%
OTIS Mock AIME 2024-20251.8%—
Omni-MATH—16.3%

Knowledge Claude 3 Haiku leads

Claude 3 Haiku: 17.3 (#285), Mixtral 8x22B: 15.1 (#293)

BenchmarkClaude 3 HaikuMixtral 8x22B
GPQA Diamond36.3%34.1%
LMArena Expert11481113
MMLU73.8%77.8%
MMLU-Pro—46%
Confabulations34.2%—
GPQA (HELM)—33.4%

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), Mixtral 8x22B: —

BenchmarkClaude 3 HaikuMixtral 8x22B
LMArena Vision950—
ScienceQA72%—

Multilingual Claude 3 Haiku leads

Claude 3 Haiku: 36.0 (#243), Mixtral 8x22B: 32.8 (#255)

BenchmarkClaude 3 HaikuMixtral 8x22B
LMArena Non-English11781128
LMArena Chinese11551116
LMArena French11951166
LMArena German11741141
LMArena Japanese11021037
LMArena Korean11091057
LMArena Russian12041158
LMArena Spanish11661151

Instruction Following Claude 3 Haiku leads

Claude 3 Haiku: 61.3 (#247), Mixtral 8x22B: 57.7 (#266)

BenchmarkClaude 3 HaikuMixtral 8x22B
LMArena Instruction Following11731147
IFEval—72.4%

Long Context Claude 3 Haiku leads

Claude 3 Haiku: 36.1 (#237), Mixtral 8x22B: 34.7 (#247)

BenchmarkClaude 3 HaikuMixtral 8x22B
LMArena Longer Query11901144

Writing & Preference Mixtral 8x22B leads

Claude 3 Haiku: 29.7 (#291), Mixtral 8x22B: 36.9 (#262)

BenchmarkClaude 3 HaikuMixtral 8x22B
LMArena Text11951162
LMArena Creative Writing11571141
LMArena Multi-Turn11901130
EQ-Bench Creative Writing717—
WildBench—71.1%

Frequently asked questions

Is Claude 3 Haiku better than Mixtral 8x22B?

Mixtral 8x22B is the stronger model overall, scoring 27.1 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Mixtral 8x22B better for coding?

Claude 3 Haiku scores higher on coding benchmarks: 26.4 versus 24.2 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Mixtral 8x22B share?

28 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Mixtral 8x22B has 34.

Related comparisons

Go deeper