Mistral Medium 3.5
Mistral • text#239 of 616 in intelligence
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...
Specifications
Context Window
262K tokens
Input Price/1M
$1.50
#589 of 744
Output Price/1M
$7.50
Parameters
—
Speed
145 tok/s
#85 of 602
Latency (TTFT)
2.3s
Max Output
210K tokens
Cost per Task
5.0
AA Score / US$ · higher = better
Benchmarks
Mistral Medium 3.5 results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
Agentic
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Terminal-Bench Hard | 33.0 | 100.0 | — |
Coding
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Coding Index | 46.9 | 100.0 | Artificial Analysis official API |
| SciCode | 40.0 | 100.0 | — |
| LiveCodeBench | 10.0 | 100.0 | — |
Knowledge
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU-Pro | 49.0 | 100.0 | — |
Long Context
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA-LCR | 61.0 | 100.0 | — |
overall
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| LMArena Elo | 1426.0 | 2000.0 | Crowdsourced blind pairwise comparisons |
| AA Intelligence Index | 14.9 | 100.0 | Artificial Analysis official API |
Reasoning
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| GPQA Diamond | 75.0 | 100.0 | Artificial Analysis official API |
| IFBench | 69.0 | 100.0 | — |
| HLE | 13.0 | 100.0 | — |
Tool Use
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Tau²-Bench | 94.0 | 100.0 | — |
Information
- Release date
- April 29, 2026
- Tool Calling
- ✅ Supported
- Vision
- ✅ Supported
- Audio
- ❌ Not supported
Full Analysis: Mistral Medium 3.5
What is Mistral Medium 3.5?
Mistral Medium 3.5 is an AI model developed by Mistral, classified as a text model. It focuses on text processing and natural language generation. As a proprietary model, it is available via Mistral's cloud API. With a context window of 262K tokens, it is suitable for processing long documents such as contracts, books, and complete codebases.
Pricing & Costs in 2026
Mistral Medium 3.5 is usage-based, priced at $1.5/1M input tokens and $7.5/1M output tokens. For context: 1 million tokens is approximately 750,000 words, or about 10 average-length books. The mid-range pricing balances quality and cost for most professional applications.
Benchmarks & Performance
Mistral Medium 3.5 was evaluated on 12 different benchmarks, covering categories like Agentic, Coding, Knowledge, Long Context, overall, Reasoning, Tool Use. Results show exceptional performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Recommended Use Cases
Mistral Medium 3.5 specializes in text, offering advanced capabilities for creating and processing text content.
Comparison with Alternatives
In the 2026 AI model ecosystem, Mistral Medium 3.5 competes directly with similarly capable models. Mistral competes in this segment against OpenAI, Anthropic, Google, and Meta. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Frequently Asked Questions
What is Mistral Medium 3.5?
Mistral Medium 3.5 is an AI model developed by Mistral. It is a text model.
How much does Mistral Medium 3.5 cost?
Mistral Medium 3.5 costs $1.5/1M input tokens and $7.5/1M output tokens. For heavy usage (e.g., a chatbot handling 100k messages/month), costs can range from $10 to $1,000 depending on volume.
How does Mistral Medium 3.5 compare with other models?
In available benchmarks, Mistral Medium 3.5 scored: Terminal-Bench Hard: 33/100, AA Coding Index: 46.9/100, SciCode: 40/100. See the full table above for a detailed comparison.
Is Mistral Medium 3.5 open source?
No, Mistral Medium 3.5 is a proprietary model from Mistral. It is available via cloud API. For open source alternatives, check our open source model ranking.
What is Mistral Medium 3.5 best for?
Mistral Medium 3.5 excels at multimodal tasks including text and vision. With its large context window, it handles long documents, codebases, and extended conversations. It supports tool calling for API integrations and automation.
Last updated: September 12, 2026 • View methodology →