Noometry

Model comparison

Claude Sonnet 4 vs Mistral Large

Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 31.6 on the Noometry Index. Mistral Large costs 2.0× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.

Last verified . 38 shared benchmarks.

Claude Sonnet 4 Anthropic

40.6

Rank #139 Confirmed

Mistral Large Mistral AI

31.6

Rank #258 Confirmed

Summary

  • They share 38 benchmarks with published results for both. Claude Sonnet 4 scores higher in 8 categories and Mistral Large in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 4 leads 41.5 to 17.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Claude Sonnet 4 and 8.5% for Mistral Large.
  • Mistral Large is cheaper at $2 / $6 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
  • Claude Sonnet 4 accepts more context: 200K tokens versus 131K.
  • Mistral Large has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4Mistral Large
ProviderAnthropicMistral AI
Noometry Index40.631.6
Released2025-05-222024-02-26
WeightsProprietaryOpen
Context window200K131K
Max output64K16K
Input $ / M tokens$3$2
Output $ / M tokens$15$6
Results tracked5851

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

Category by category

Coding Claude Sonnet 4 leads

Claude Sonnet 4: 44.0 (#70), Mistral Large: 33.8 (#240)

BenchmarkClaude Sonnet 4Mistral Large
SciCode40%36.2%
LMArena Coding14141277
ALE-Bench655.35264.7
SWE-bench Verified (bash only)64.9%—
Aider Polyglot61.3%—
GSO4.9%—
WeirdML46.1%—
BigCodeBench Instruct—30%
LiveBench Coding—47.1%
BigCodeBench Complete—38.3%
HumanEval+—62.2%
MBPP+—59.5%

Agentic & Tool Use Claude Sonnet 4 leads

Claude Sonnet 4: 38.3 (#29), Mistral Large: 28.4 (#83)

BenchmarkClaude Sonnet 4Mistral Large
Berkeley Function Calling Leaderboard—38.4%
TheAgentCompany33.1%—
Cybench35%—
DeepResearch Bench46.6%—
OSWorld43.9%—
METR Time Horizons62%—

Reasoning Claude Sonnet 4 leads

Claude Sonnet 4: 23.0 (#169), Mistral Large: 15.4 (#305)

BenchmarkClaude Sonnet 4Mistral Large
SimpleBench45.5%22.5%
CritPt0.3%0%
LMArena Hard Prompts13721257
DTBench77.1%65.1%
LMCA29%16.7%
Epoch Capabilities Index141.69128.52
ForecastBench60.257.1
ARC-AGI-25.9%—
Kagi LLM Benchmark73%—
ARC-AGI-140%—
EnigmaEval3.1%—
LiveBench Reasoning—43.5%
LiveBench Data Analysis—50.1%
LiveBench—48.4%

Math Claude Sonnet 4 leads

Claude Sonnet 4: 41.5 (#71), Mistral Large: 17.1 (#285)

BenchmarkClaude Sonnet 4Mistral Large
OTIS Mock AIME 2024-202571.1%8.5%
Omni-MATH60.2%28.1%
LMArena Math13751262
MATH Level 584.4%50.3%
FrontierMath (Feb 2025 set)4.1%0.3%
LiveBench Math—42.5%
FrontierMath Tier 4 (v1)0%—

Knowledge Claude Sonnet 4 leads

Claude Sonnet 4: 41.6 (#99), Mistral Large: 30.0 (#224)

BenchmarkClaude Sonnet 4Mistral Large
GPQA Diamond79.2%51.3%
MMLU-Pro84.3%59.9%
Confabulations13.2%21.4%
Vectara Hallucination Rate10.3%4.5%
GPQA (HELM)70.6%43.5%
LMArena Expert13711232
Humanity's Last Exam7.8%—
MMLU—80%

Multimodal Not comparable

Claude Sonnet 4: 25.6 (#116), Mistral Large: —

BenchmarkClaude Sonnet 4Mistral Large
LMArena Vision1191—
GeoBench37%—
VPCT34%—
MindCube44.8%—

Multilingual Claude Sonnet 4 leads

Claude Sonnet 4: 46.9 (#151), Mistral Large: 40.1 (#214)

BenchmarkClaude Sonnet 4Mistral Large
LMArena Non-English13331237
LMArena Chinese13511240
LMArena French13641324
LMArena German13311254
LMArena Japanese13011187
LMArena Korean12931202
LMArena Russian13551257
LMArena Spanish13561268

Instruction Following Claude Sonnet 4 leads

Claude Sonnet 4: 71.8 (#141), Mistral Large: 68.1 (#186)

BenchmarkClaude Sonnet 4Mistral Large
IFEval84%87.7%
LMArena Instruction Following13751249
LiveBench Instruction Following—67.9%

Long Context Mistral Large leads

Claude Sonnet 4: 33.6 (#254), Mistral Large: 38.3 (#194)

BenchmarkClaude Sonnet 4Mistral Large
LMArena Longer Query13981262
Fiction.LiveBench46.9%—

Writing & Preference Claude Sonnet 4 leads

Claude Sonnet 4: 57.3 (#127), Mistral Large: 40.9 (#237)

BenchmarkClaude Sonnet 4Mistral Large
LMArena Text13511266
LMArena Creative Writing13451243
Short-Story Creative Writing81.4%69%
EQ-Bench Creative Writing1483985
WildBench83.8%80.1%
LMArena Multi-Turn13761260
LiveBench Language—39.4%

Frequently asked questions

Is Claude Sonnet 4 better than Mistral Large?

Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 31.6 on the Noometry Index. Mistral Large costs 2.0× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4 or Mistral Large?

Mistral Large is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Claude Sonnet 4 lists at $3 and $15.

Is Claude Sonnet 4 or Mistral Large better for coding?

Claude Sonnet 4 scores higher on coding benchmarks: 44.0 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4 does, with 200K tokens against 131K.

How many benchmarks do Claude Sonnet 4 and Mistral Large share?

38 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Mistral Large has 51.

Related comparisons

Go deeper