Mistral Large 2 (Jul) — benchmark results

July 2024 Mistral Large 2 model row. Provider: Mistral. Released 2024-07-24. Access: API.

Unified ELO 1578 ± 15, rank #537 of 1776 rated models, from 135 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
NVIDIA LLM Robustness - MATH Accuracy71.14Accuracy (%)100
NVIDIA LLM Robustness - MATH Consistency67.71Consistency (%)100
Polish EQ-Bench78.07EQ-Bench Score100
LogicKor - Coding9.92Score (0-10)99.3
Open PL LLM - Generative72.21Average Generative Score (%)99.3
Open PL LLM Leaderboard69.11Average Score (%)99.3
Open PL LLM - Multiple Choice65.08Average Multiple-Choice Score (%)98.6
LogicKor - Understanding9.92Score (0-10)98.2
LLMZSZL Leaderboard67.17Score98
Open PL LLM - RAG75.78Average RAG Score (%)97.9
LogicKor - Multi-Turn9.16Score (0-10)97.8
HREF48.39Average HREF Score (%)97

Interactive version: theaggregate.ai/model?slug=mistral-large-2-jul · How the rankings work · Data refreshed daily, snapshot 2026-07-22.