Mistral Medium 3
Mistral AI🇫🇷 France
Mistral Medium tier model balancing performance and cost. Strong coding and reasoning at a mid-tier price point.
Context window131K tokens
Input / 1M tokens$0.4
Output / 1M tokens$2
Version History
mistral-medium-2505major
Mistral Medium 3 launches with vision, strong coding, and mid-tier pricing. Outperforms GPT-4o mini on reasoning benchmarks at comparable cost.
Benchmark Scores
Full leaderboard →64.8%
GPQA
84.0%
HumanEval
73.2%
MATH
82.0%
MMLU
67.2%
MMLU-Pro
75.0 tokens_per_sec
Speed (tok/s)