Skip to content

Mistral apache_2_0 Released Jun 10, 2025 Updated

Magistral Medium

ToolsGuide Scores, rankings, test results and price.

Model summary

  • Text #243 / 419

    215 / 1,000

    ToolsGuide Score· votes 182, tests 262

  • Price per 1M tokens

    No listed price

Summary

Magistral Medium is Mistral's model, released Jun 10, 2025. It's ranked in 1 category and does best at text: #243 of 419, with a ToolsGuide Score of 215 against a median of 252.

It has published results on 6 tests.

Specifications

Creator
Mistral
Licence
apache_2_0
Released
Jun 10, 2025
Context window
–
Input price
–
Output price
–
Tests reported
6
Settings ranked
Magistral Medium (2506)

Model comparison

Against the ten best text models.

Text score

ToolsGuide Score out of 1,000 · Higher is better

Input price

USD per 1M input tokens · Lower is better

Leaderboards

Where Magistral Medium sits among the top 20 in each category.

Text

#243 of 419 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full text leaderboard →

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Against its nearest rivals

Text prompts by kind · ToolsGuide Score from votes · hover for values

Text

Magistral Medium (2506) · hover a bar for its rank

Test results

Every test Magistral Medium has a published result on, out of 100%, with its rank among the models that took it.

  • GPQA

    #152 / 265

    Graduate-level science questions written to be hard to look up.

    70.8%

    Self-reported

  • AIME 2025

    #101 / 124

    Competition maths problems from the 2025 American Invitational Mathematics Exam.

    64.9%

    Self-reported

  • Humanity's Last Exam

    #105 / 115

    Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions

    9.0%

    Self-reported · In the text score· In the vision score

  • LiveCodeBench

    #48 / 77

    LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.

    50.3%

    Self-reported

  • AIME 2024

    #37 / 54

    American Invitational Mathematics Examination 2024, consisting of 30 challenging mathematical reasoning problems from AIME I and AIME II competitions. Each problem requires an integer answer between 0-999 and tests advanced mathematical reasoning across algebra, geometry, combinatorics, and number theory. Used as a benchmark for evaluating mathematical reasoning capabilities in large language models at Olympiad-level difficulty.

    73.6%

    Self-reported

  • Aider-Polyglot

    #18 / 22

    A coding benchmark that evaluates LLMs on 225 challenging Exercism programming exercises across C++, Go, Java, JavaScript, Python, and Rust. Models receive two attempts to solve each problem, with test error feedback provided after the first attempt if it fails. The benchmark measures both initial problem-solving ability and capacity to edit code based on error feedback, providing an end-to-end evaluation of code generation and editing capabilities across multiple programming languages.

    47.1%

    Self-reported