---
title: "Qwen 3.6 27B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Qwen 3.6."
source: "https://rankedagi.com/models/qwen-3-6-27b"
---

# Qwen 3.6

| Field | Value |
| --- | --- |
| Organization | Alibaba |
| License | Open Source |
| Type | Thinking |
| Size | 27B |
| Version | Latest |
| Released | 2026-04-22 |
| Context window | 256K |
| Input cost per million tokens | $0.6 |
| Output cost per million tokens | $3.6 |
| Model ID | qwen3.6-27b |
| Last updated | 2026-04-25T00:20:49.103Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 69.7% | RankedAGI Coding Score |  |
| SWEBench Pro | coding | 53.5% | Diverse Agentic Coding |  |
| SWEBench Multilingual | coding | 71.3% |  |  |
| SWEBench Verified | coding | 77.2% | Agentic Coding | https://www.swebench.com/index.html |
| Terminal-Bench 2.0 | coding | 59.3% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| RankedAGI Agentic | Agents | 67.7% | RankedAGI Agentic Score |  |
| LiveCodeBench v6 | coding | 83.9% | LiveCodeBench v6 - Evaluation of Large Language Models for Code |  |
| RankedAGI Reasoning | reasoning | 65.7% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 24.0% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 87.8% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| AIME 2026 | math | 94.1% | AIME 2026 Competition Math | https://matharena.ai/?comp=aime--aime_2026&view=problem |
| MMLU Pro | knowledge | 86.2% | Graduate-level visual problem-solving |  |
| RankedAGI Math | math | 74.5% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 63.0% | Overall RankedAGI score |  |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://qwen.ai/blog?id=qwen3.6-27b |