readable AI benchmarks (simplified)

readable AI benchmarks

Mistral

Mistral Small 3.2

non-reasoning · open weights · Jun 20, 2025

Mistral Small 3.2 has a Quality Score of 18.7, ranking 413th among 551 scored models. Per 1M tokens, pricing is $0.075 input and $0.200 output. It accepts text and image input, outputs text, and has a 128k token context window. Its Reliability Score is 24.7, ranking 379th among 553 scored models, below average (total average: 35.6).

Quality Score18.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability24.7
Cache Discountnot available

Model specification

Reasoning
non-reasoning
Input modalities
text, image
Output modalities
text
Context window
128k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.075
Output
$0.200
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
8.2
Coding
not available
Agentic
not available
Omniscience
-50.6
Correct
14.8%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 80.3%

Correct 14.8%Incorrect 65.4%Partial / not attempted 19.8%

Artificial Analysis benchmarks

GDPval-AA v2
0%
τ³-Banking
6%
SciCode
29%
Humanity’s Last Exam
4%
GPQA Diamond
51%
CritPt
0%
AA-Omniscience
25%
AA-LCR
20%

Similar models

Support me! Patreon