readable AI benchmarks

Mistral

Mistral Large 3

non-reasoning · open weights · Dec 2, 2025

Quality Score19.6
Value Score16.7
Reliability30.2
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
$0.500
Output
$1.50
Cached Input
not available
Cached Output
not available
Cost per task
$0.081

Capability

Intelligence
15.9
Coding
20.1
Agentic
5.5
Omniscience
-39.6
Correct
24.9%
Blended price
$0.600

Answer outcomes

Correct 24.9%Incorrect 64.5%Abstained 10.5%

Artificial Analysis benchmarks

GDPval-AA v2
7%
τ³-Banking
6%
Terminal-Bench v2.1
12%
SciCode
36%
Humanity’s Last Exam
4%
GPQA Diamond
68%
CritPt
0%
AA-Omniscience
30%
AA-LCR
35%

Similar models