Mistral Medium 3.5
Mistral Medium 3.5 is Mistral AI's flagship merged model unifying reasoning, coding, and vision, with configurable reasoning effort and open weights.
Model Overview
Capabilities, design details, and architectural traits
Mistral Medium 3.5 - Mistral AI's First Flagship Merged Model
Mistral Medium 3.5 is Mistral AI's first flagship model built by merging capabilities that were previously split across separate models. Instead of keeping dedicated models for chat, reasoning, and coding, Mistral folded Mistral Medium 3.1, Magistral, and Devstral 2 into a single unified model.
| Trait | Description |
|---|---|
| Merged Architecture | Combines instruction-following, reasoning, and coding into one set of weights, replacing three previously separate models |
| Configurable Reasoning Effort | Switches between a fast instant-reply mode and an extended reasoning mode, set per request rather than through a separate model |
| Vision Encoder | Built from scratch to handle images of variable size and aspect ratio |
Open Weights License
Mistral Medium 3.5 is released as open weights under a Modified MIT License. This sets it apart from most other flagship-class models, which are distributed only as closed, API-only weights.
Benchmark Performance
Independent evaluations · Artificial Analysis
Accuracy & Capability Details
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
Compare Models Side-by-Side
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | MistralHost Mistral Medium 3.5 | ||
|---|---|---|---|
| General Info | |||
| Provider | Mistral | Anthropic | Anthropic |
| Release Date | April 29, 2026 | June 9, 2026 | May 28, 2026 |
| Knowledge Cutoff | — | — | — |
| Context & Limits | |||
| Context Window | 262K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | $1.50 Best Input Pricing | $10 | $5 |
| Output Pricing | $7.50 Best Output Pricing | $50 | $25 |
| Modalities | |||
| Inputs | textimagefile | textimagefile | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 29.9 | 59.9 Best Intelligence Index | 55.7 |
| Coding Index | 46.9 | 76.5 Best Coding Index | 74.3 |
| Agentic Index | 19.0 | 52.8 Best Agentic Index | 47.2 |
GPQA Benchmark
Graduate-level reasoning and expert Q&A evaluation.
Humanity's Last Exam
Extremely difficult logical reasoning and knowledge.
IFBench Instruction
Evaluation of strict instruction following.
Benchmark scores are independent evaluations sourced from Artificial Analysis. Intelligence, Coding, and Agentic indices reflect composite performance ratings (0–100).