readable AI benchmarks (simplified)

readable AI benchmarks

Mistral

Magistral Medium 1

reasoning · closed weights · Jun 10, 2025

Magistral Medium 1 has a Quality Score of 25.2, ranking 305th among 551 scored models. It has a 40k token context window. Its Reliability Score is 36.5, ranking 246th among 553 scored models, above average (total average: 35.6).

Quality Score25.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability36.5
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
40k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
not available
Output
not available
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
9.1
Coding
not available
Agentic
not available
Omniscience
-26.9
Correct
20.3%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 67.6%

Correct 20.3%Incorrect 47.3%Partial / not attempted 32.4%

Artificial Analysis benchmarks

Humanity’s Last Exam
10%
GPQA Diamond
68%
CritPt
0%
AA-Omniscience
37%
AA-LCR
0%

Similar models

Support me! Patreon