Magistral Small 1.2
Open multimodal reasoning model for transparent analysis of text and images
ECI STANDING#147 of 266
SCORE131.41127.11–133.67 CI
FRONTIER LAGLaunched 12.2 months behindScores about what o1-mini did in September 2024.
SCORES LIKE THESE MODELS
Full Epoch Capabilities Index ranking ↗Llama 4 MaverickMeta AI · Apr 2025132.2
Mistral Small 3.2Mistral AI · Jun 2025131.74Gemini 1.5 Pro (Sept 2024)Google DeepMind · Sep 2024131.73
Grok-2 (Dec 2024)xAI · Dec 2024130.48
RELEASE DATESep 18, 2025
WEIGHTSOpen weights
CONTEXT WINDOW131.1K
MAX OUTPUT131.1K
REASONINGYes
TOOL CALLINGYes
INPUTStext, image
OUTPUTStext
Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.