modelbenchmark.io

magistral-small-1-2

Mistral · magistral-small-1-2

Compare

Specification

mistral listing

Context
40K
Max output
40K
Released
Knowledge cutoff
Retires
2026-07-31
Open weights
Input
Output

Price

US dollars per million tokens · mistral list price

Input
$0.50
Output
$1.50

Quality

3 benchmarks · 1 source

Composite
27th
percentile of 334 scored models
Rank
243 / 334
±0.10 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
one configuration only
reasoning28th2/4 bench
math27th1/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
OTIS Mock AIME 2024-202528.1 ±5.6defaultEpoch AI2026-08-30
GPQA diamond47.6 ±2.6defaultEpoch AI2026-08-30
Chess Puzzles3.0 ±1.7defaultEpoch AI2026-08-30

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
mistralvendor$0.50$1.5040K40K2026-07-31

More from Mistral

most-hosted first