Phi 3.5 Mini Instruct — Benchmarks

Benchmark scores for Phi 3.5 Mini Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #12 of 123 open modelscomposite 69.4/100 across 4 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro47.9%#67 / 119#173 / 259
BoolQ78.0%#16 / 33#43 / 77

Math

BenchmarkScoreOpen rankAll models
GSM8K86.2%#9 / 60#13 / 93

Reasoning

BenchmarkScoreOpen rankAll models
PIQA81.0%#16 / 35#31 / 60

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

Phi 3.5 Mini Instruct Benchmarks — Scores & Rankings | llmrun