Ministral 8B — benchmark results

Mistral's 8B edge model ('les Ministraux') with a 128K context and interleaved sliding-window attention. Provider: Mistral. Released 2024-10-16. Access: Open.

Unified ELO 1452 ± 27, rank #987 of 1776 rated models, from 25 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
TinyQABenchmark (core-en)80.8Exact Match50
Konkur 1404 - Mathematics33.91Accuracy (%, text-only)42.1
Software Engineering Arena - Model Arena998Elo Rating38.6
SnakeBench18.7TrueSkill Rating35.3
ChLogic92.03English (self-reported)33.3
LLM-WikiRace24.73Average Success (%)32.1
Konkur 1404 - Foreign Language34.62Accuracy (%, text-only)31.6
EHRBench56.48Overall Acc (%) (self-reported)30
TRLawBench60.6Stage 1 accuracy (self-reported)29
AI Chess Leaderboard (Reasoning)560Elo25.9
IDP Leaderboard58.7Avg Score (%)24
Konkur 1404 - Humanities30.65Accuracy (%, text-only)18.4

Interactive version: theaggregate.ai/model?slug=ministral-8b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.