readable AI benchmarks

Mistral

Ministral 3 3B

non-reasoning · open weights · Dec 2, 2025

Quality Score6.3
Value Score8.3
Reliability18.0
Cache Discountnot available

Model specification

Reasoning
non-reasoning
Input modalities
text, image
Output modalities
text
Context window
256k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.100
Output
$0.100
Cached Input
not available
Cached Output
not available
Cost per task
$0.130

Capability

Intelligence
7.1
Coding
4.8
Agentic
1.6
Omniscience
-64.0
Correct
9.0%
Blended price
$0.100

Answer outcomes

Correct 9.0%Incorrect 73.0%Abstained 18.0%

Artificial Analysis benchmarks

GDPval-AA v2
0%
τ³-Banking
5%
Terminal-Bench v2.1
0%
SciCode
14%
Humanity’s Last Exam
5%
GPQA Diamond
36%
CritPt
0%
AA-Omniscience
18%
AA-LCR
16%

Similar models