readable AI benchmarks (simplified)

readable AI benchmarks

Mistral

Devstral Small (May '25)

non-reasoning · open weights · May 21, 2025

Devstral Small (May '25) has a Quality Score of 17.5, ranking 438th among 551 scored models. It has a 256k token context window. Its Reliability Score is 21.6, ranking 433rd among 553 scored models, below average (total average: 35.6).

Quality Score17.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability21.6
Cache Discountnot available

Model specification

Reasoning
non-reasoning
Input modalities
none
Output modalities
none
Context window
256k tokens
Weights
open 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
8.7
Coding
not available
Agentic
not available
Omniscience
-56.8
Correct
15.9%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 88.5%

Correct 15.9%Incorrect 72.6%Partial / not attempted 11.5%

Artificial Analysis benchmarks

Humanity’s Last Exam
4%
GPQA Diamond
43%
CritPt
0%
AA-Omniscience
22%
AA-LCR
32%

Similar models

Support me! Patreon