The Model Index
Up to four models

Claude Sonnet 4 vs Mistral Medium 3.5

On the index (GPT-4 = 100), Claude Sonnet 4 scores 133 and Mistral Medium 3.5 131. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Claude Sonnet 4
Presets
Claude Sonnet 4
133117–149
WeightsClosed
ReleasedMay 2025
Price in / out–
Context–
Core tests taken4 of 9
Mistral Medium 3.5
131114–148
WeightsOpen
ReleasedApr 2026
Price in / out$1.5 / $7.5
Context262K
Core tests taken1 of 9

Claude Sonnet 4 and Mistral Medium 3.5 are too close to call (2 points apart, within the uncertainty).

Test by testthird-party results

Claude Sonnet 4Mistral Medium 3.5
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProCODINGWeirdMLWeirdMLAGENTSDTBenchDTBenchLMCALMCAPROFESSIONAL WORKCorpFin v2CorpFin v2MedCodeMedCodeMedScribeMedScribeMortgageTaxMortgageTaxTaxEval v2TaxEval v2
Every result as a table
TestClaude Sonnet 4Mistral Medium 3.5
Reasoning & knowledge
GPQA Diamond (Vals AI)75.0%34.8%
MMLU Pro83.9%75.3%
Coding
WeirdML46.1%43.7%
Agents
DTBench77.1%75.5%
LMCA29.0%26.1%
Professional work
CorpFin v261.2%58.8%
MedCode35.0%33.8%
MedScribe72.4%67.7%
MortgageTax62.5%28.9%
TaxEval v272.0%68.0%
Task length · METR37 sec

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG