---
title: "Mistral Medium 3 Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Mistral Medium 3."
source: "https://rankedagi.com/models/mistral-medium-3"
---

# Mistral Medium 3

| Field | Value |
| --- | --- |
| Organization | Mistral |
| Version | Latest |
| Released | 2025-05-07 |
| Input cost per million tokens | $0.4 |
| Output cost per million tokens | $2 |
| Last updated | 2026-04-23T16:25:37.523Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 42.9% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 31.3% | RankedAGI Agentic Score |  |
| RankedAGI Reasoning | reasoning | 36.3% | RankedAGI Reasoning Score |  |
| Text Arena | general | 1369 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| HumanEval | coding | 92.1% | HumanEval coding benchmark |  |
| MMLU Pro | knowledge | 77.2% | Graduate-level visual problem-solving |  |
| MMMU | imaging | 66.1% | Multimodal Understanding College-level visual problem-solving |  |
| Instruction Following Evaluation | instruction-following | 89.4% | Instruction Following Evaluation |  |
| RankedAGI Math | math | 50.5% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 42.0% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 588 | Office Tasks (Artificial Analysis) |  |
| SvelteBench old | coding | 72.2% | SvelteBench - Benchmark for Svelte (Old v1) | https://khromov.github.io/svelte-bench/v1/v1-benchmark-results-merged.html |
| Code DesignArena | Design | 1134 |  | https://www.designarena.ai/leaderboard/code |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://mistral.ai/news/mistral-medium-3 |