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
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| SciCode | 17.0% | #48 / 50 | #153 / 155 |
Knowledge
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| MMLU-Pro | 74.3% | #29 / 119 | #88 / 259 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| AIME 2024/2025 | 7.8% | #55 / 74 | #223 / 270 |
| MATH Level 5 | 62.3% | #12 / 32 | #53 / 108 |
| FrontierMath | 0.0% | #12 / 12 | #101 / 101 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| GPQA Diamond | 51.8% | #47 / 83 | #209 / 291 |
| ARC-AGI | 0.5% | #16 / 16 | #199 / 200 |
| CritPt | 0.0% | #44 / 50 | #152 / 167 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.