Mistral Large 3

Release Date: 12/2/2025

Vals Index

Accuracy (Vals Index)

34.86% ± 1.63

Latency (Vals Index)

316.23s

Cost/Test (Vals Index)

$0.10

Context Window

256k

Max Output Tokens

256k

Input Modality

Hyperparameter settings
Default Provider : Mistral AI

Temperature

0.065

Top P

Default

Top K

Default

Max Output Tokens

256,000

Show rankings only among open weight models

Benchmarks

Accuracy

Rankings

0.0%

± 1.63
42/ 45

0.0%

± 1.28
30/ 30

0.0%

± 0.96
20/ 50

0.0%

± 0.96
34/ 100

0.0%

± 2.18
43/ 49

0.0%

± 0.99
58/ 72

0.0%

± 2.81
49/ 51

0.0%

± 0.87
31/ 107

0.0%

± 0.88
66/ 96

0.0%

± 2.37
67/ 102

0.0%

± 1.46
39/ 52

0.0%

± 1.15
77/ 108

0.0%

± 0.46
61/ 119

0.0%

± 0.35
67/ 95

0.0%

± 0.47
60/ 101

0.0%

± 1.14
51/ 69

0.0%

± 2.21
42/ 44

0.0%

± 3.05
54/ 56
Contact us
Or send us an email at contact@vals.ai
Proprietary Benchmarks (contact us to get access)
Academic Benchmarks

Read about our methodology.