Llama 4 Scout — benchmark results
Meta Llama 4 Scout model row. Provider: Meta. Released 2025-04-05. Access: Open.
Unified ELO 1457 ± 14, rank #964 of 1776 rated models, from 249 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AGC-Bench - sdat | 0.67 | Dataset z-score | 98.8 |
| AGC-Bench - unfun_corpus | 0.73 | Dataset z-score | 93.6 |
| AGC-Bench - c3_crosstalk | 1.07 | Dataset z-score | 89 |
| AGC-Bench - outline_to_story | 1.11 | Dataset z-score | 88.9 |
| AGC-Bench - creatset | 1.24 | Dataset z-score | 85.4 |
| AGC-Bench - scimon | 0.69 | Dataset z-score | 85.2 |
| AndroidWorld | 91.4 | Success Rate pass@1 (%) | 82.9 |
| LLM Stats (ChartQA) | 88.8 | Score (%) | 82.6 |
| AGC-Bench - irfl | 0.69 | Dataset z-score | 78.1 |
| MMMU Benchmark | 69.4 | Validation Score | 77.8 |
| AGC-Bench - story_generation_rocstories | 0.57 | Dataset z-score | 76.8 |
| LLM Stats (DocVQA) | 94.4 | Score (%) | 74 |
Interactive version: theaggregate.ai/model?slug=llama-4-scout · How the rankings work · Data refreshed daily, snapshot 2026-07-22.