Mistral: Mistral Medium 3.5
Analysis Summary
Mistral Medium 3.5 is a mid-tier model from Mistral with an intelligence index of 29.9 and a coding index of 35.4, sitting just below the top tier but with a strong agentic index of 63.7 and an excellent tau2 score of 0.942. It supports vision, tool use, function calling, and a 262K context window, giving it broad capability coverage for business use.
Instruction following is a clear strength, with an ifbench score of 0.688 and long-context reasoning of 0.61, both above average for this tier. This makes it well suited to client-facing content generation, document analysis, and structured output tasks. The vision modality adds value for teams processing mixed media.
At $1.50 input and $7.50 output, it is priced in the mid-range. Businesses looking for a capable, multimodal model from a well-supported provider that handles both content and agentic tasks without flagship pricing will find Mistral Medium 3.5 a practical choice.
Assessed June 19, 2026
Editorial notes
Mistral Medium 3.5 combines strong instruction following, vision support, tool use, and a 262K context window with a competitive agentic index, making it a capable all-rounder for business content and automation workflows.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Mistral: Mistral Medium 3.5 compares
Mistral: Mistral Medium 3.5 ranks #80 of 380 AI models we track for overall intelligence, #28 of 94 for coding, #47 of 292 for agentic tasks. Its 262K-token context window is larger than 81% of the models we list. At $1.50 per million input tokens it is cheaper than 18% of comparable models.
About Mistral: Mistral Medium 3.5
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..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Mistral: Mistral Medium 3.5 stack up?
Compare side-by-side with other specialist models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $1.50 | $0.001500 |
| Output | $7.50 | $0.007500 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Mistral: Mistral Medium 3.5
How much does Mistral: Mistral Medium 3.5 cost?
Mistral: Mistral Medium 3.5 costs $1.50 per million input tokens and $7.50 per million output tokens.
What is the context window of Mistral: Mistral Medium 3.5?
Mistral: Mistral Medium 3.5 has a context window of 262,144 tokens (262K).
Is Mistral: Mistral Medium 3.5 good for coding?
On our coding benchmark index, Mistral: Mistral Medium 3.5 ranks #28 of 94 models, placing it in the broader range of the field for code generation and debugging.
What can Mistral: Mistral Medium 3.5 do?
Mistral: Mistral Medium 3.5 supports image/vision input, tool use, and function calling.
Who created Mistral: Mistral Medium 3.5?
Mistral: Mistral Medium 3.5 is developed by Mistral and was released on April 30, 2026.
