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
| Benchmark | Score | Rank |
|---|---|---|
| Aider Polyglot | 15.6% | #14 / 17 |
Knowledge
| Benchmark | Score | Rank |
|---|---|---|
| Humanity's Last Exam | 5.7% | #4 / 4 |
Math
| Benchmark | Score | Rank |
|---|---|---|
| AIME 2024/2025 | 20.6% | #12 / 29 |
| MATH Level 5 | 73.0% | #7 / 31 |
| FrontierMath | 0.7% | #11 / 12 |
Reasoning
| Benchmark | Score | Rank |
|---|---|---|
| GPQA Diamond | 67.0% | #11 / 41 |
| ARC-AGI | 4.4% | #9 / 10 |
| SimpleBench | 27.7% | #10 / 15 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.