---
title: "Pixtral Large 123B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Pixtral Large."
source: "https://rankedagi.com/models/pixtral-large-123b"
---

# Pixtral Large

| Field | Value |
| --- | --- |
| Organization | Mistral |
| License | Proprietary |
| Size | 123B |
| Version | Latest |
| Released | 2024-11-18 |
| Context window | 128K |
| Input cost per million tokens | $2 |
| Output cost per million tokens | $6 |
| Last updated | 2025-04-16 22:14:46.146909+00 |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 37.2% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 39.4% | RankedAGI Agentic Score |  |
| RankedAGI Reasoning | reasoning | 41.9% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 52.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| HumanEval | coding | 82.0% | HumanEval coding benchmark |  |
| MMLU | knowledge | 85.0% | Image Reasoning |  |
| Hughes Hallucination Evaluation | safety | 6.6% | 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 | 73 | Artificial Analysis Quality Index (third-party composite, deprecated) |  |
| RankedAGI Math | math | 48.5% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 43.0% | Overall RankedAGI score |  |