Mistral announced Magistral, their first reasoning model that shows transparent step-by-step thinking across multiple languages, released in both open-source (Small, 24B parameters) and enterprise (Medium) versions with Magistral Medium scoring 73.6% pass@1 on AIME2024 benchmark
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
Mistral announced Magistral, their first reasoning model that shows transparent step-by-step thinking across multiple languages, released in both open-source (Small, 24B parameters) and enterprise (Medium) versions with Magistral Medium scoring 73.6% pass@1 on AIME2024 benchmark