Devstral Small 2

Release Date: 12/9/2025

Accuracy (Average)

22.84%

Latency (Average)

3742.71s

Avg. Cost (In/Out)

0.1 / 0.3

Context Window

256k

Max Output Tokens

256k

Input Modality

Hyperparameter settings
Default Provider : Mistral

Temperature

0.2

Top P

Default

Top K

Default

Max Output Tokens

256,000

Show rankings only among open weight models

Benchmarks

Accuracy

Rankings

0.0%

± 1.78
47/ 53

0.0%

± 1.16
92/ 110
Contact us
Or send us an email at contact@vals.ai
Proprietary Benchmarks (contact us to get access)
Academic Benchmarks

Read about our methodology.