---
title: "Qwen 3 A22B 235B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Qwen 3 A22B."
source: "https://rankedagi.com/models/qwen-3-a22b-235b"
---

# Qwen 3 A22B

| Field | Value |
| --- | --- |
| Organization | Alibaba |
| License | Open Source |
| Size | 235B |
| Version | Latest |
| Released | 2025-07-21 |
| Context window | 262K |
| Model ID | qwen3-235b-a22b-instruct-2507 |
| Last updated | 2026-04-23T16:27:06.714Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 48.5% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 38.3% | RankedAGI Agentic Score |  |
| LiveCodeBench v6 | coding | 51.8% | LiveCodeBench v6 - Evaluation of Large Language Models for Code |  |
| Aider Polyglot | coding | 57.3% | Aider Polyglot Code Completion Benchmark |  |
| RankedAGI Reasoning | reasoning | 50.2% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 77.5% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| AIME 2025 | math | 70.3% | AIME 2025 Competition Math |  |
| MMLU Pro | knowledge | 83.0% | Graduate-level visual problem-solving |  |
| Instruction Following Evaluation | instruction-following | 88.7% | Instruction Following Evaluation |  |
| RankedAGI Math | math | 65.0% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 48.2% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 781 | Office Tasks (Artificial Analysis) |  |
| SvelteBench old | coding | 55.6% | SvelteBench - Benchmark for Svelte (Old v1) | https://khromov.github.io/svelte-bench/v1/v1-benchmark-results-merged.html |
| Code DesignArena | Design | 1103 |  | https://www.designarena.ai/leaderboard/code |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://x.com/Alibaba_Qwen/status/1947344511988076547 |