readable AI benchmarks

Mistral

Devstral 2

non-reasoning · open weights · Dec 9, 2025

Quality Score20.4
Value Score24.1
Reliability26.6
Cache Discountnot available

Model specification

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

Token prices USD per 1M tokens

Input
$0.0000
Output
$0.0000
Cached Input
not available
Cached Output
not available
Cost per task
$0.0000

Capability

Intelligence
19.2
Coding
31.3
Agentic
10.6
Omniscience
-46.7
Correct
20.8%
Blended price
$0.0000

Answer outcomes

Correct 20.8%Incorrect 67.5%Abstained 11.7%

Artificial Analysis benchmarks

GDPval-AA v2
12%
τ³-Banking
11%
Terminal-Bench v2.1
30%
SciCode
33%
Humanity’s Last Exam
4%
GPQA Diamond
59%
CritPt
0%
AA-Omniscience
27%
AA-LCR
31%

Similar models