---
title: "Llama 3.2 1B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Llama 3.2."
source: "https://rankedagi.com/models/llama-3.2-1b"
---

# Llama 3.2

| Field | Value |
| --- | --- |
| Organization | Meta |
| License | Open Source |
| Size | 1B |
| Version | Latest |
| Released | 2024-09-25 |
| Context window | 128K |
| Knowledge cutoff | 2023-12-01 |
| Input cost per million tokens | $0.04 |
| Output cost per million tokens | $0.08 |
| Last updated | 2025-04-16 22:14:46.146909+00 |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 13.3% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 11.0% | RankedAGI Agentic Score |  |
| ChatArena (LMSYS) | coding | 1009 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| RankedAGI Reasoning | reasoning | 19.7% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 14.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1044 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| MMLU Pro | knowledge | 11.9% | Graduate-level visual problem-solving |  |
| MMLU | knowledge | 49.3% | Image Reasoning |  |
| Hughes Hallucination Evaluation | safety | 20.7% | 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 |
| Artificial Analysis Quality Index | general | 28 | Artificial Analysis Quality Index (third-party composite, deprecated) |  |
| RankedAGI Math | math | 33.6% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 26.6% | Overall RankedAGI score |  |