readable AI benchmarks

Mistral

Ministral 3 14B

non-reasoning · open weights · Dec 2, 2025

Quality Score10.1
Value Score12.0
Reliability16.8
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
$0.200
Output
$0.200
Cached Input
not available
Cached Output
not available
Cost per task
$0.158

Capability

Intelligence
11.2
Coding
14.4
Agentic
2.2
Omniscience
-66.4
Correct
13.6%
Blended price
$0.200

Answer outcomes

Correct 13.6%Incorrect 80.0%Abstained 6.5%

Artificial Analysis benchmarks

GDPval-AA v2
0%
τ³-Banking
7%
Terminal-Bench v2.1
10%
SciCode
24%
Humanity’s Last Exam
5%
GPQA Diamond
57%
CritPt
0%
AA-Omniscience
17%
AA-LCR
25%

Similar models