---
title: "Qwen 2.5 Max Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Qwen 2.5 Max."
source: "https://rankedagi.com/models/qwen-2.5-max"
---

# Qwen 2.5 Max

| Field | Value |
| --- | --- |
| Organization | Alibaba |
| License | Proprietary |
| Version | Latest |
| Released | 2025-01-28 |
| Context window | 32K |
| Knowledge cutoff | 2024-09-01 |
| Input cost per million tokens | $1.6 |
| Output cost per million tokens | $6.4 |
| Model ID | qwen-max-2025-01-25 |
| Last updated | 2026-05-04T01:34:22.840Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 36.4% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 33.2% | RankedAGI Agentic Score |  |
| ChatArena (LMSYS) | coding | 1291 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| Aider Polyglot | coding | 21.8% | Aider Polyglot Code Completion Benchmark |  |
| LiveBench Coding Score (old) | coding | 64.4% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 37.7% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 60.1% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1357 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| HumanEval | coding | 73.2% | HumanEval coding benchmark |  |
| NYT Connections Extended | reasoning | 18.0% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| MMLU Pro | knowledge | 76.1% | Graduate-level visual problem-solving |  |
| LiveBench Average | general | 62.3% | LiveBench Average Score old version |  |
| LiveBench Coding 25.4 | coding | 33.8% | LiveBench Coding Score 2025-04 | https://livebench.ai/ |
| LiveBench Data Analysis | general | 67.9% | LiveBench Data Analysis Score | https://livebench.ai/ |
| LiveBench Language | general | 56.3% | LiveBench Language Score | https://livebench.ai/ |
| RankedAGI Math | math | 42.8% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 40.8% | Overall RankedAGI score |  |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://qwenlm.github.io/blog/qwen2.5-max/ |