---
title: "Qwen 2.5 72B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Qwen 2.5."
source: "https://rankedagi.com/models/qwen-2.5-72b"
---

# Qwen 2.5

| Field | Value |
| --- | --- |
| Organization | Alibaba |
| License | Open Source |
| Size | 72B |
| Version | Latest |
| Released | 2024-09-19 |
| Context window | 128K |
| Knowledge cutoff | 2024-09-01 |
| Input cost per million tokens | $0.38 |
| Output cost per million tokens | $0.57 |
| Last updated | 2025-04-16 22:14:46.146909+00 |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 23.7% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 23.8% | Agentic Coding | https://www.swebench.com/index.html |
| RankedAGI Agentic | Agents | 22.6% | RankedAGI Agentic Score |  |
| LiveCodeBench v5 | coding | 31.1% | LiveCodeBench - Evaluation of Large Language Models for Code |  |
| ChatArena (LMSYS) | coding | 1247 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| LiveBench Coding Score (old) | coding | 57.6% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 33.2% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 49.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1259 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| HumanEval | coding | 86.6% | HumanEval coding benchmark |  |
| HumanEval+ | coding | 51.2% | HumanEval+ benchmark |  |
| NYT Connections Extended | reasoning | 11.1% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| MMLU Pro | knowledge | 71.1% | Graduate-level visual problem-solving |  |
| MMLU | knowledge | 86.8% | Image Reasoning |  |
| Hughes Hallucination Evaluation | safety | 4.7% | 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 |
| LiveBench Average | general | 51.4% | LiveBench Average Score old version |  |
| LiveBench Data Analysis | general | 48.4% | LiveBench Data Analysis Score | https://livebench.ai/ |
| LiveBench Language | general | 35.0% | LiveBench Language Score | https://livebench.ai/ |
| Artificial Analysis Quality Index | general | 75 | Artificial Analysis Quality Index (third-party composite, deprecated) |  |
| RankedAGI Math | math | 43.4% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 34.8% | Overall RankedAGI score |  |