Llama 4 Scout Base — benchmark results
Base Llama 4 Scout checkpoint. Provider: Meta. Released 2025-04-05. Access: Open.
Unified ELO 1460 ± 12, rank #954 of 1776 rated models, from 634 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MEGA-Bench Task - Flowchart Code Generation | 77.8 | Task Score (%) | 100 |
| MEGA-Bench Task - OCR Resume Employer Plain | 78.6 | Task Score (%) | 98.8 |
| MEGA-Bench Task - Places365 Scene Type Classification | 100 | Task Score (%) | 98.8 |
| EuroEval Swedish NLU - Swerec | 80.1 | Sentiment classification Score (%) | 95.9 |
| MEGA-Bench Task - Annoying Word Search | 0.4 | Task Score (%) | 95.3 |
| MEGA-Bench Task - Camera Trajectory To Video Selection | 64.3 | Task Score (%) | 94.2 |
| MEGA-Bench Task - GUI Act Web Single | 7.8 | Task Score (%) | 93 |
| MEGA-Bench Task - Graph Hamiltonian Cycle | 52.4 | Task Score (%) | 93 |
| MEGA-Bench Task - Long String Letter Recognition | 21.4 | Task Score (%) | 93 |
| MEGA-Bench Task - OCR Math Equation | 71.4 | Task Score (%) | 93 |
| MEGA-Bench Task - Remaining Playback Time Calculation | 28.6 | Task Score (%) | 93 |
| MEGA-Bench Task - CLEVR Arithmetic | 68.4 | Task Score (%) | 91.9 |
Interactive version: theaggregate.ai/model?slug=llama-4-scout-base · How the rankings work · Data refreshed daily, snapshot 2026-07-22.