Mistral 7B Instruct (v0.1) — benchmark results

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

Unified ELO 1303 ± 23, rank #1526 of 1776 rated models, from 100 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
NPHardEval - GCP20.91Accuracy (%)100
NPHardEval - GCP D58Accuracy (%)90.9
NPHardEval - TSP D62.73Accuracy (%)81.8
Open Medical LLM - PubMedQA75.8Accuracy (%)78.4
FastEval42.66Total Score62.5
SpeechMap Compliance70.4% Requests Completed62.1
PIQA82.2Accuracy (%)60.8
EuroEval Portuguese NLU - MultiWikiQA PT70.47Reading comprehension Score (%)60.1
EuroEval Spanish NLU - Sentiment Headlines ES41.35Sentiment classification Score (%)56.6
EuroEval Italian NLU - Sentipolc1650.71Sentiment classification Score (%)52.9
EuroEval Spanish NLU - MLQA ES59.98Reading comprehension Score (%)51.8
CyberBench (NLP)58.38Avg Score (%)50

Interactive version: theaggregate.ai/model?slug=mistral-7b-instruct-v0-1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.