← All benchmarks

Mistral Small 4 (Reasoning)

Mistral · Released 2026-03-16 · Independent benchmark scores from Artificial Analysis

Intelligence Index
11.3
Output speed
167.8
tokens/sec
Blended price
$0.26
per 1M tokens
Time to first token
0.57s

Model metadata

Model ID3fd96175-4ef1-434c-8795-f873aec2abc1
Slugmistral-small-4
Release date2026-03-16
ProviderMistral
Provider slugmistral
Output speed167.8 tok/s
Time to first token0.57s
Time to first answer12.49s
Blended price ($/1M)$0.26
Input price ($/1M)$0.15
Output price ($/1M)$0.60

All evaluation scores (17)

aime
aime 25
artificial analysis coding index26.60
artificial analysis intelligence index11.30
artificial analysis math index
gpqa76.9%
hle9.9%
ifbench48.2%
lcr49.7%
livecodebench
math 500
mmlu pro
scicode38.8%
tau banking4.9%
tau241.2%
terminalbench hard17.4%
terminalbench v2 121.0%

Source: artificialanalysis.ai/models/mistral-small-4

Benchmark data from Artificial Analysis.