readable AI benchmarks

Mistral

Devstral Small 2

non-reasoning · open weights · Dec 9, 2025

Quality Score16.8
Value Score21.0
Reliability21.1
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
$0.0000
Output
$0.0000
Cached Input
not available
Cached Output
not available
Cost per task
$0.0000

Capability

Intelligence
17.7
Coding
29.3
Agentic
10.8
Omniscience
-57.7
Correct
15.8%
Blended price
$0.0000

Answer outcomes

Correct 15.8%Incorrect 73.5%Abstained 10.7%

Artificial Analysis benchmarks

GDPval-AA v2
12%
τ³-Banking
11%
Terminal-Bench v2.1
30%
SciCode
29%
Humanity’s Last Exam
3%
GPQA Diamond
53%
CritPt
0%
AA-Omniscience
21%
AA-LCR
27%

Similar models