Mistral 7B v0.1 — Benchmarks

Benchmark scores for Mistral 7B v0.1 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #25 of 73 open modelscomposite 53.3/100 across 5 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
HellaSwag81.0%#13 / 42#26 / 76
MMLU-Pro30.9%#95 / 119#225 / 259
MMLU62.5%#40 / 76#86 / 136

Math

BenchmarkScoreOpen rankAll models
GSM8K54.4%#27 / 59#40 / 93

Reasoning

BenchmarkScoreOpen rankAll models
BIG-Bench Hard56.1%#13 / 37#20 / 50

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