---
title: "Llama 3.1 405B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Llama 3.1."
source: "https://rankedagi.com/models/llama-3.1-405b"
---

# Llama 3.1

| Field | Value |
| --- | --- |
| Organization | Meta |
| License | Open Source |
| Size | 405B |
| Version | Latest |
| Released | 2024-07-23 |
| Context window | 128K |
| Knowledge cutoff | 2023-12-01 |
| Input cost per million tokens | $5 |
| Output cost per million tokens | $15 |
| Last updated | 2026-05-04T01:34:22.840Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 26.6% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 24.5% | Agentic Coding | https://www.swebench.com/index.html |
| RankedAGI Agentic | Agents | 24.4% | RankedAGI Agentic Score |  |
| LiveCodeBench v5 | coding | 28.4% | LiveCodeBench - Evaluation of Large Language Models for Code |  |
| ChatArena (LMSYS) | coding | 1260 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| LiveBench Coding Score (old) | coding | 42.6% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 35.6% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 51.1% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1266 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| HumanEval | coding | 89.0% | HumanEval coding benchmark |  |
| NYT Connections Extended | reasoning | 16.2% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| MMLU Pro | knowledge | 73.3% | Graduate-level visual problem-solving |  |
| MMLU | knowledge | 87.0% | Image Reasoning |  |
| Hughes Hallucination Evaluation | safety | 3.9% | Computed using Vectara's Hallucination Evaluation Model, also known as HHEM. This evaluates how often an LLM introduces hallucinations when summarizing a document. | https://github.com/vectara/hallucination-leaderboard |
| AidanBench | general | 778 | AidanBench Score |  |
| LiveBench Average | general | 58.6% | LiveBench Average Score old version |  |
| Instruction Following Evaluation | instruction-following | 88.6% | Instruction Following Evaluation |  |
| LiveBench Data Analysis | general | 54.5% | LiveBench Data Analysis Score | https://livebench.ai/ |
| LiveBench Language | general | 45.5% | LiveBench Language Score | https://livebench.ai/ |
| Artificial Analysis Quality Index | general | 72 | Artificial Analysis Quality Index (third-party composite, deprecated) |  |
| RankedAGI Math | math | 44.3% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 36.3% | Overall RankedAGI score |  |