Mistral 7B Instruct — benchmark results

Provider: Mistral. Released 2023-09-27. Access: Open.

Unified ELO 1237 ± 32, rank #1648 of 1776 rated models, from 67 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
PlantMarkerBench69Valid F1 (self-reported)87.5
SWE-Arena1002Elo Score80.6
LogicKor - Math4.71Score (0-10)56.2
SnakeBench21.4TrueSkill Rating49.7
LogicKor - Coding7Score (0-10)46.2
LogicKor - Multi-Turn4.88Score (0-10)34.1
FanOutQA42.71Accuracy (%, closedbook loose)33.3
CritPt0Accuracy (self-reported)30.3
LogicKor4.9Score (0-10)28.3
AA CritPt0Accuracy (%)27.1
LogicKor - Grammar3.57Score (0-10)25.2
LogicKor - Writing5.14Score (0-10)25.2

Interactive version: theaggregate.ai/model?slug=mistral-7b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.