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.

Coding

BenchmarkScoreRank
Aider Polyglot15.6%#14 / 17

Knowledge

BenchmarkScoreRank
Humanity's Last Exam5.7%#4 / 4

Math

BenchmarkScoreRank
AIME 2024/202520.6%#12 / 29
MATH Level 573.0%#7 / 31
FrontierMath0.7%#11 / 12

Reasoning

BenchmarkScoreRank
GPQA Diamond67.0%#11 / 41
ARC-AGI4.4%#9 / 10
SimpleBench27.7%#10 / 15

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