Magistral Medium 1.2 (09/2025)

Release Date: 9/18/2025

Accuracy (Average)

50.06%

Latency (Average)

362.74s

Avg. Cost (In/Out)

2 / 5

Context Window

128k

Max Output Tokens

128k

Input Modality

Hyperparameter settings
Default Provider : Mistral

Temperature

0.7

Top P

Default

Top K

Default

Max Output Tokens

128,000

Benchmarks

Accuracy

Rankings

0.0%

± 0.98
96/ 117

0.0%

± 0.99
67/ 81

0.0%

± 0.96
100/ 123

0.0%

± 2.44
88/ 117

0.0%

± 0.44
53/ 55

0.0%

± 1.13
62/ 123

0.0%

± 0.56
114/ 120

0.0%

± 0.43
105/ 116

0.0%

± 1.15
62/ 77
Contact us
Or send us an email at contact@vals.ai

License type:

Proprietary (contact us to get access)
Industry Partner
Academic

Read our methodology.