Mistral Medium 3.5
ModelOpen sourceActiveby Mistral AI · family “mistral-medium”
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex... (description from the OpenRouter listing)
in: textin: imagein: fileout: textReasoningTool useStructured output
Epoch Capabilities Index
141.4 #104 of 268
90% CI 138.6 – 143.5
Released
28 Apr 2026
Context window
262K tokens
Max output
210K tokens
Input $ / 1M tokens
$1.50
Output $ / 1M tokens
$7.50
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source
Benchmark results (6)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| LMCA | agents | 26.1% | 40% | — | — | External ↗ |
| DTBench | reasoning | 75.5% | 77% | — | — | External ↗ |
| Surface Evolver Bench | science | 26.9% | 28% | — | — | External ↗ |
| FrontierCode | coding | 8.0% | 15% | — | — | External ↗ |
| ProofBench | math | 9.0% | 9% | — | — | External ↗ |
| WeirdML | coding | 43.7% ±0.0 | 47% | — | — | External ↗ |
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
5 observations (OpenRouter listing + Internet Archive snapshots). History accumulates with every ingest run; a single point means no change has been observed yet.
Events
- Open release5mo agoMistral releases Mistral Medium 3.5Epoch AI Benchmarking Hub