The Model Index
Up to four models

GPT-5.5 vs Mistral Medium 3.5

On the index (GPT-4 = 100), GPT-5.5 scores 172 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 GPT-5.5
Presets
GPT-5.5
172156–188
WeightsClosed
ReleasedApr 2026
Price in / out$5.0 / $30
Context1.05M
Core tests taken6 of 9
Mistral Medium 3.5
131114–148
WeightsOpen
ReleasedApr 2026
Price in / out$1.5 / $7.5
Context262K
Core tests taken1 of 9

GPT-5.5 leads Mistral Medium 3.5 by 41 points, ahead on 1 of 1 shared core tests, at 3.8× the price.

Test by testthird-party results

GPT-5.5Mistral Medium 3.5
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMATHSSurface Evolver BenchSurface Evolver BenchCODINGCode MigrationCode MigrationSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1WeirdMLWeirdMLAGENTSDTBenchDTBenchLMCALMCAPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)CorpFin v2CorpFin v2EMBEMBLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribeMortgageTaxMortgageTaxTax Agent BenchTax Agent BenchTaxEval v2TaxEval v2
Every result as a table
TestGPT-5.5Mistral Medium 3.5
Reasoning & knowledge
GPQA Diamond (Vals AI)93.2%34.8%
MMLU Pro88.1%75.3%
Maths
Surface Evolver Bench88.1%26.9%
Coding
Code Migration45.2%5.1%
SWE-bench82.6%66.4%
Vibe Code Bench v1.169.8%2.9%
WeirdML84.9%43.7%
Agents
DTBench96.0%75.5%
LMCA54.3%26.1%
Professional work
Finance Agent (v2)51.8%32.1%
CorpFin v268.4%58.8%
EMB64.5%11.2%
Legal Research Bench40.4%9.1%
MedCode49.1%33.8%
MedScribe86.9%67.7%
MortgageTax68.8%28.9%
Tax Agent Bench21.8%4.5%
TaxEval v275.0%68.0%

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

This page as a chartDownload PNG