Mistral Large Instruct 2411 — Benchmarks

Benchmark scores for Mistral Large Instruct 2411 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #43 of 78 open modelscomposite 42.8/100 across 5 benchmarks in 3 categories · methodology

Instruction Following

BenchmarkScoreOpen rankAll models
LMArena Text1305.4#99 / 182#258 / 391

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro67.9%#42 / 144#108 / 257

Math

BenchmarkScoreOpen rankAll models
MATH Level 550.3%#14 / 39#62 / 107
AIME 2024/20257.8%#61 / 82#226 / 270

Reasoning

BenchmarkScoreOpen rankAll models
DTBench60.8%#45 / 67#165 / 210
GPQA Diamond51.3%#50 / 94#211 / 289

Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.