Mistral Medium 3
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
ECI STANDING#138 of 266
SCORE134.07130.83–135.56 CI
FRONTIER LAGLaunched 7.8 months behindScores about what o1-mini did in September 2024.
SCORES LIKE THESE MODELS
Full Epoch Capabilities Index ranking ↗Gemini 2.0 Flash (Dec 2024)Google DeepMind,Google · Dec 2024134.71
Gemini 2.0 Flash (Feb 2025)Google DeepMind,Google · Feb 2025134.69
Gemini 2.5 Flash-Lite (Jun 2025)Google DeepMind · Jun 2025133.93
Claude 3.5 Sonnet (October 2024)Anthropic · Oct 2024133.55
RELEASE DATEMay 7, 2025
WEIGHTSClosed weights
CONTEXT WINDOW131.1K
MAX OUTPUT131.1K
REASONINGNo
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.