---
title: "Qwen 3.5 A17B 397B Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Qwen 3.5 A17B."
source: "https://rankedagi.com/models/qwen-3-5-a17b-397b"
---

# Qwen 3.5 A17B

| Field | Value |
| --- | --- |
| Organization | Alibaba |
| License | Open Source |
| Type | Thinking |
| Size | 397B |
| Version | Latest |
| Released | 2026-02-16 |
| Last updated | 2026-04-27T16:42:00.776Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 68.2% | RankedAGI Coding Score |  |
| SWEBench Pro | coding | 50.9% | Diverse Agentic Coding |  |
| SWEBench Multilingual | coding | 69.3% |  |  |
| SWEBench Verified | coding | 76.2% | Agentic Coding | https://www.swebench.com/index.html |
| Terminal-Bench 2.0 | coding | 52.5% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| RankedAGI Agentic | Agents | 61.9% | RankedAGI Agentic Score |  |
| Code Arena | coding | 1388 | Code Arena Elo Score | https://arena.ai/leaderboard/code |
| LiveCodeBench v6 | coding | 83.6% | LiveCodeBench v6 - Evaluation of Large Language Models for Code |  |
| RankedAGI Reasoning | reasoning | 67.5% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 28.7% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 88.4% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| AIME 2026 | math | 93.3% | AIME 2026 Competition Math | https://matharena.ai/?comp=aime--aime_2026&view=problem |
| MMLU Pro | knowledge | 87.8% | Graduate-level visual problem-solving |  |
| RankedAGI Math | math | 74.9% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 61.8% | Overall RankedAGI score |  |
| Toolathlon | Agents | 38.3% | Benchmark to assess language agents' general tool use in realistic environments. | https://toolathlon.xyz/introduction |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://qwen.ai/blog?id=qwen3.5 |