Mistral: Mistral Large 3 2512
Analysis Summary
Mistral: Mistral Large 3 2512 sits in the Efficient tier on our leaderboard, ranked #189 of 544 published models on overall intelligence. At $0.500 input and $1.50 output per 1M tokens, it is among the most expensive on the market. It offers a generous context window for extended reasoning and code review and supports tool use, function calling, and vision.
Editorial notes
Mistral Large 3 2512 benchmarks well below its name suggests, with a low intelligence index and weak math and coding scores; vision and tool use are present but overall capability is limited.
Assessed May 5, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
Mistral Large 3 2512 is Mistralās most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Mistral: Mistral Large 3 2512 stack up?
Compare side-by-side with other efficient models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.50 | $0.000500 |
| Output | $1.50 | $0.001500 |
Live Performance
Live endpoint metrics ā refreshed every 30 minutes.
