Mistral Medium 3.5

Release Date: 4/29/2026

Accuracy (Average)

46.73%

Latency (Average)

259.46s

Avg. Cost (In/Out)

1.5 / 7.5

Context Window

262k

Max Output Tokens

80k

Input Modality

Hyperparameter settings
Default Provider : Mistral

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%

± 0.97
58/ 105

0.0%

± 0.60
14/ 18

0.0%

± 1.15
44/ 57

0.0%

± 2.01
52/ 57

0.0%

± 0.84
71/ 74

0.0%

± 3.36
34/ 55

0.0%

± 0.92
73/ 111

0.0%

± 2.39
102/ 105

0.0%

± 0.42
79/ 104

0.0%

± 4.90
41/ 62
Contact us
Or send us an email at contact@vals.ai
Proprietary Benchmarks (contact us to get access)
Academic Benchmarks

Read about our methodology.