Mistral Medium 3
ModelActiveby Mistral AI · family “mistral-medium”
Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost... (description from the OpenRouter listing)
in: textin: imagein: fileout: textTool useStructured output
Epoch Capabilities Index
134.1 #140 of 268
90% CI 129.3 – 135.4
Released
7 May 2025
Context window
131K tokens
Max output
105K tokens
Input $ / 1M tokens
$0.40
Output $ / 1M tokens
$2.00
Cached input $ / 1M
$0.040
Each benchmark shown separately with its own source
Benchmark results (7)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| DTBench | reasoning | 62.3% | 63% | — | — | External ↗ |
| FrontierMath-2025-02-28-Privatesuperseded | math | 0.3% ±0.3 | 1% | — | 7 May 2025 | Epoch ↗ |
| Lech Mazur Writing | other | 77.3% | 90% | — | — | External ↗ |
| HLE | knowledge | 4.5% | 8% | — | — | External ↗ |
| OTIS Mock AIME 2024-2025 | math | 32.2% ±6.0 | 32% | — | 7 May 2025 | Eval log ↗ |
| GPQA diamond | science | 59.5% ±2.8 | 62% | — | 7 May 2025 | Eval log ↗ |
| MATH level 5 | math | 81.6% ±0.9 | 83% | — | 7 May 2025 | Epoch ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
13 observations (OpenRouter listing + Internet Archive snapshots). History accumulates with every ingest run; a single point means no change has been observed yet.
Events
No events recorded yet.