Mistral: Mistral Large 3 2512
Mistral Large 3 2512 has benchmark data but scores poorly across reasoning, coding, and agentic tasks — well below what would be expected from a 'Large' model at this price point. With a 262K context window and multimodal support it has some utility, but the performance profile does not justify the cost for most business applications.
Assessment date: March 12, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Mistral Large 3 2512 is Mistral’s 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
Architecture
| Modality | Text + Image → Text |
| Tokenizer | Mistral |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
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 — refreshed every 30 minutes.
