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: #59 of 78 open modelscomposite 33.3/100 across 14 benchmarks in 4 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SciCode | 33.1% | #46 / 62 | #141 / 161 |
| Aider Polyglot | 15.6% | #15 / 18 | #62 / 69 |
| WeirdML | 24.5% | #39 / 46 | #143 / 161 |
Instruction Following
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| LMArena Text | 1326.9 | #85 / 182 | #226 / 391 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| Humanity's Last Exam | 5.7% | #4 / 4 | #41 / 49 |
| MMLU-Pro | 80.5% | #24 / 144 | #62 / 257 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| MATH Level 5 | 73.0% | #7 / 39 | #42 / 107 |
| AIME 2024/2025 | 20.6% | #52 / 82 | #212 / 270 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| DTBench | 61.9% | #40 / 67 | #158 / 210 |
| LMCA | 15.9% | #38 / 53 | #148 / 172 |
| GPQA Diamond | 67.0% | #34 / 94 | #172 / 289 |
| SimpleBench | 27.7% | #17 / 25 | #82 / 101 |
| CritPt | 0.0% | #51 / 62 | #155 / 172 |
| ARC-AGI | 4.4% | #15 / 16 | #195 / 200 |
| ARC-AGI-2 | 0.0% | #14 / 16 | #187 / 190 |
| Fiction.LiveBench | 46.2% | #18 / 24 | #48 / 58 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.