readable AI benchmarks (simplified)

readable AI benchmarks

Mistral

Devstral Medium

non-reasoning · closed weights · Jul 10, 2025

Devstral Medium has a Quality Score of 24.0, ranking 319th among 551 scored models. It accepts text input, outputs text, and has a 256k token context window. Its Reliability Score is 34.2, ranking 267th among 553 scored models, below average (total average: 35.6).

Quality Score24.0coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability34.2
Cache Discountnot available

Model specification

Reasoning
non-reasoning
Input modalities
text
Output modalities
text
Context window
256k 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
9.0
Coding
not available
Agentic
not available
Omniscience
-31.6
Correct
18.9%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 69.3%

Correct 18.9%Incorrect 50.4%Partial / not attempted 30.7%

Artificial Analysis benchmarks

Humanity’s Last Exam
4%
GPQA Diamond
49%
CritPt
0%
AA-Omniscience
34%
AA-LCR
32%

Similar models

Support me! Patreon