Llama 4 Maverick 17B 128E Instruct — Benchmarks

Benchmark scores for Llama 4 Maverick 17B 128E Instruct aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #61 of 73 open modelscomposite 29.6/100 across 9 benchmarks in 4 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
Aider Polyglot15.6%#15 / 18#62 / 69

Knowledge

BenchmarkScoreOpen rankAll models
Humanity's Last Exam5.7%#4 / 4#38 / 46
MMLU-Pro80.5%#22 / 119#62 / 259

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202520.6%#16 / 34#108 / 155
MATH Level 573.0%#7 / 32#42 / 108
FrontierMath0.7%#11 / 12#94 / 101

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond67.0%#15 / 46#94 / 182
ARC-AGI4.4%#9 / 10#153 / 158
SimpleBench27.7%#13 / 19#71 / 90

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