The Model Index
Up to four models

GPT-5.2 vs Mistral Large 3

On the index (GPT-4 = 100), GPT-5.2 scores 162 and Mistral Large 3 117. 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-5.2
Presets
GPT-5.2
162146–178
WeightsClosed
ReleasedDec 2025
Price in / out$1.75 / $14
Context400K
Core tests taken6 of 9
Mistral Large 3
11799–135
WeightsOpen
ReleasedDec 2025
Price in / out$0.50 / $1.5
Context262K
Core tests taken0 of 9

GPT-5.2 leads Mistral Large 3 by 45 points, at 6.4× the price.

Test by testthird-party results

GPT-5.2Mistral Large 3
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProSimpleBenchSimpleBenchMATHSMGSMMGSMCODINGLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchAGENTSDTBenchDTBenchLMCALMCAPROFESSIONAL WORKCorpFin v2CorpFin v2LegalBenchLegalBenchMortgageTaxMortgageTaxTaxEval v2TaxEval v2
Every result as a table
TestGPT-5.2Mistral Large 3
Reasoning & knowledge
GPQA Diamond (Vals AI)91.7%68.4%
MMLU Pro86.2%79.8%
MMMU Pro86.7%66.2%
SimpleBench45.8%20.4%
Maths
MGSM94.0%85.4%
Coding
LiveCodeBench85.4%55.3%
SWE-bench75.8%41.4%
Agents
DTBench90.9%65.1%
LMCA43.9%16.7%
Professional work
CorpFin v265.9%61.0%
LegalBench82.8%79.1%
MortgageTax67.1%52.1%
TaxEval v275.8%73.1%
Task length · METR45 sec

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

This page as a chartDownload PNG