Mistral Small 4

Release Date: 3/16/2026

Vals Index

Accuracy (Vals Index)

29.07% ± 1.60

Latency (Vals Index)

553.59s

Cost/Test (Vals Index)

$1.39

Context Window

256k

Max Output Tokens

256k

Input Modality

Hyperparameter settings
Default Provider : Mistral AI

Temperature

0.7

Top P

Default

Top K

Default

Max Output Tokens

256,000

Reasoning Effort

high

Show rankings only among open weight models

Benchmarks

Accuracy

Rankings

0.0%

± 1.60
34/ 35

0.0%

± 0.00
43/ 43

0.0%

± 3.99
56/ 61
Contact us
Or send us an email at contact@vals.ai
Proprietary Benchmarks (contact us to get access)
Academic Benchmarks

Read about our methodology.