Llama 4 Scout 17B 16E Instruct — Benchmarks

Benchmark scores for Llama 4 Scout 17B 16E Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #99 of 123 open modelscomposite 31/100 across 8 benchmarks in 4 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
SciCode17.0%#48 / 50#153 / 155

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro74.3%#29 / 119#88 / 259

Math

BenchmarkScoreOpen rankAll models
AIME 2024/20257.8%#55 / 74#223 / 270
MATH Level 562.3%#12 / 32#53 / 108
FrontierMath0.0%#12 / 12#101 / 101

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond51.8%#47 / 83#209 / 291
ARC-AGI0.5%#16 / 16#199 / 200
CritPt0.0%#44 / 50#152 / 167

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