Back

Mistral

Magistral Medium 1.2

ReasoningClosed weights
Intelligence
11.8
Rank 377 of 744 measured models
Coding
21.3
Rank 219 of 298 measured models
Context window
128K
Rank 773 of 1199 measured models

Magistral Medium 1.2 scores 11.8 on the Artificial Analysis Intelligence Index, ranking 377th of 744 measured models. The closest models on this index are Qwen3 Coder 480B A35B Instruct (11.9), Sonar Reasoning Pro (11.8), and HyperNova 60B 2605 (High, Based on gpt-oss-120b) (11.7).

Artificial Analysis Indices
Intelligence11.8
Rank 377 of 744 measured models
Coding21.3
Rank 219 of 298 measured models
Math82.0
Rank 60 of 270 measured models
Standard Benchmarks
MMLU Pro81.5%
Rank 86 of 349 measured models
GPQA Diamond73.9%
Rank 280 of 619 measured models
HLE10.3%
Rank 330 of 664 measured models
LiveCodeBench75.0%
Rank 47 of 343 measured models
AIME 202582.0%
Rank 60 of 270 measured models
IFBench43.0%
Rank 243 of 450 measured models
AA-LCR53.0%
Rank 314 of 575 measured models
TerminalBench Hard12.9%
Rank 219 of 432 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy