Mistral Medium 3.5

Release Date: 4/29/2026

Vals Index

Accuracy (Vals Index)

52.77% ± 1.98

Latency (Vals Index)

543.29s

Cost/Test (Vals Index)

$2.06

Context Window

262k

Max Output Tokens

80k

Input Modality

Hyperparameter settings
Default Provider : Mistral AI

Temperature

0.7

Top P

0.95

Top K

Default

Max Output Tokens

80,000

Reasoning Effort

high

Show rankings only among open weight models

Benchmarks

Accuracy

Rankings

0.0%

± 1.98
33/ 47

0.0%

± 1.54
29/ 33

0.0%

± 1.06
53/ 54

0.0%

± 0.97
57/ 104

0.0%

± 2.88
34/ 51

0.0%

± 1.15
43/ 56

0.0%

± 2.01
51/ 56

0.0%

± 0.84
70/ 73

0.0%

± 3.36
33/ 54

0.0%

± 0.92
72/ 110

0.0%

± 2.39
101/ 104

0.0%

± 0.42
78/ 103

0.0%

± 4.90
40/ 60
Contact us
Or send us an email at contact@vals.ai
Proprietary Benchmarks (contact us to get access)
Academic Benchmarks

Read about our methodology.