Mistral Large 3

Release Date: 12/2/2025

Benchmarked by Vals Logo
Vals Index

Mistral's latest flagship model

Avg. Accuracy

50.01%

Latency

470.13s

Cost (In/Out)

0.5 / 1.5

Context Window

256k

Max Output Tokens

256k

Input Modality

Benchmarks

Accuracy

Rankings

Vals Index

0.0%

25/ 30

CaseLaw (v2)

0.0%

13/ 57

CorpFin

0.0%

15/ 77

Finance Agent

0.0%

38/ 56

MortgageTax

0.0%

43/ 56

SAGE

0.0%

33/ 35

TaxEval (v2)

0.0%

21/ 87

AIME

0.0%

48/ 78

GPQA

0.0%

45/ 79

IOI

0.0%

28/ 40

LiveCodeBench

0.0%

56/ 86

LegalBench

0.0%

45/ 102

MedQA

0.0%

58/ 86

MGSM

0.0%

68/ 75

MMLU Pro

0.0%

39/ 79

MMMU

0.0%

36/ 53

SWE-bench

0.0%

35/ 45

Terminal-Bench

0.0%

39/ 47

Academic Benchmarks
Proprietary Benchmarks (contact us to get access)

Join our mailing list to receive benchmark updates

Model benchmarks are seriously lacking. With Vals AI, we report how language models perform on the industry-specific tasks where they will be used.

By subscribing, I agree to Vals' Privacy Policy.