Magistral Medium 1

Magistral Medium 1

Mistral · Released Jun 10, 2025
Intelligence #651 / 756
15.2 our score
AA Index #254 / 438
9.1 Artificial Analysis
Input Price
Not priced
Output Price
Not priced
Context
Not reported

Analysis Summary

Magistral Medium 1 provides a broader evidence base than the smaller version, including mathematics, coding, terminal tasks, instruction following, and tool-oriented evaluation results. Those results point to a model that can handle selected technical problems, while its low overall intelligence measure and modest agentic evidence limit dependable multi-step performance.

It could serve supervised coding assistance, structured extraction, and technical drafting where the task is bounded and outputs receive review. The profile is not strong enough for autonomous software agents, high-stakes analysis, or polished client-facing content without a verification layer. Pricing, context capacity, speed, vision, and API details are not supplied, so adoption should follow a focused pilot rather than a general deployment.

Assessed September 7, 2026

Editorial notes

Magistral Medium 1 shows useful mathematics, coding, and terminal-task evidence for a mid-sized model, but its overall reasoning and agentic results remain limited for complex client workflows.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

DFO Verdict

Magistral Medium 1 shows useful mathematics, coding, and terminal-task evidence for a mid-sized model, but its overall reasoning and agentic results remain limited for complex client workflows.

#651 of 756 overall

Benchmark scores

GPQA Diamond 67.9%
HLE 9.5%
MMLU Pro 75.3%
MATH 500 91.7%
AIME 70%
AIME 2025 40.3%
SciCode 29.7%
LiveCodeBench 52.7%
TerminalBench Hard 9.1%
τ²-Bench 23.1%
IFBench 25.1%

Magenta = intelligence · Ink = technical/agentic · Cyan = content & long-context · Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.

9.1 Intelligence Index·40.3 Math Index

How Magistral Medium 1 compares

Magistral Medium 1 ranks #254 of 438 AI models we track for overall intelligence. Magistral Medium 1 is currently free to use via OpenRouter.

Position in the field
Intelligence: smarter than 14% of models #651
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Magistral Medium 1 $0.00 in $0.00 out
OpenAI: GPT-6 Astra $10.00 in $50.00 out
Anthropic: Claude Fable 5.1 $10.00 in $50.00 out
Claude Opus 5 $5.00 in $25.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Intelligence2.3Technical0Value0Content3.7
Performance profile

Strongest on business fit. The pulled-in value corner is the trade-off, and if the shape matters more than the price, this is your model.

Compare shapes side-by-side →

Frequently asked questions about Magistral Medium 1

How much does Magistral Medium 1 cost?

Magistral Medium 1 is currently available for free via OpenRouter.

Who created Magistral Medium 1?

Magistral Medium 1 is developed by Mistral and was released on June 10, 2025.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.