Mistral-7B-v0.1 — benchmark results

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

Unified ELO 1347 ± 8, rank #1426 of 1776 rated models, from 225 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
MMLU-by-task - Econometrics50Accuracy (%)99.8
MMLU-by-task - College Chemistry52Accuracy (%)99.3
MMLU-by-task - Medical Genetics74Accuracy (%)98.9
MMLU-by-task - Virology55.42Accuracy (%)98.8
HELM Classic - IMDB96.2Exact Match (%)98.5
MMLU-by-task - College Medicine66.47Accuracy (%)97.2
HELM Classic - Entity Matching93.81Exact Match (%)97
MMLU-by-task - Anatomy62.96Accuracy (%)97
MMLU-by-task - College Physics39.22Accuracy (%)96.7
MMLU-by-task - Nutrition75.82Accuracy (%)96.7
MMLU-by-task - Computer Security77Accuracy (%)96.4
MMLU-by-task - High School Chemistry52.71Accuracy (%)95.8

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