---
title: "Qwen 2.5 7B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Qwen 2.5."
source: "https://rankedagi.com/models/qwen-2.5-7b"
---

# Qwen 2.5

| Field | Value |
| --- | --- |
| Organization | Alibaba |
| License | Open Source |
| Size | 7B |
| Version | Latest |
| Released | 2024-09-19 |
| Context window | 128K |
| Knowledge cutoff | 2024-09-01 |
| Last updated | 2025-04-16 22:14:46.146909+00 |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 37.3% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 45.0% | RankedAGI Agentic Score |  |
| LiveBench Coding Score (old) | coding | 38.4% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 32.2% | RankedAGI Reasoning Score |  |
| Hughes Hallucination Evaluation | safety | 2.8% | 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 | 33.6% | LiveBench Average Score old version |  |
| LiveBench Data Analysis | general | 32.8% | LiveBench Data Analysis Score | https://livebench.ai/ |
| LiveBench Language | general | 15.8% | LiveBench Language Score | https://livebench.ai/ |
| RankedAGI Math | math | 47.1% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 42.0% | Overall RankedAGI score |  |