---
title: "Llama 4 Scout 109B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Llama 4 Scout."
source: "https://rankedagi.com/models/llama-4-scout-109b"
---

# Llama 4 Scout

| Field | Value |
| --- | --- |
| Organization | Meta |
| License | Open Source |
| Size | 109B |
| Version | Latest |
| Released | 2025-04-05 |
| Context window | 10M |
| Knowledge cutoff | 2024-08-01 |
| Last updated | 2026-05-04T01:34:22.840Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 28.4% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 18.5% | RankedAGI Agentic Score |  |
| LiveCodeBench v5 | coding | 32.8% | LiveCodeBench - Evaluation of Large Language Models for Code |  |
| RankedAGI Reasoning | reasoning | 35.1% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 57.2% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| MMLU Pro | knowledge | 74.3% | Graduate-level visual problem-solving |  |
| MMMU | imaging | 69.4% | Multimodal Understanding College-level visual problem-solving |  |
| RankedAGI Math | math | 41.2% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 34.9% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 280 | Office Tasks (Artificial Analysis) |  |
| SvelteBench old | coding | 15.6% | SvelteBench - Benchmark for Svelte (Old v1) | https://khromov.github.io/svelte-bench/v1/v1-benchmark-results-merged.html |
| Code DesignArena | Design | 854 |  | https://www.designarena.ai/leaderboard/code |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://ai.meta.com/blog/llama-4-multimodal-intelligence/ |