GPT-5.2vsQwen3.6

GPT-5.2
Qwen3.6
Specifications
Parameters
35B
Context window
256k
Benchmarks
Nonsense detection
BullshitBench v2
38%
Agentic coding
SWE-Bench Pro
49.5%
Coding
SWE-Bench Verified
80%Best
73.4%
Multilingual coding
SWE-Bench Multilingual
67.2%
Agentic terminal coding
Terminal-Bench 2.0
51.5%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
21.4%
Abstract reasoning
ARC-AGI-2
52.9%
Science
GPQA Diamond
92.4%Best
86%
Chart reasoning
CharXiv Reasoning
78%
Multimodal reasoning
MMMU-Pro
75.3%
Multimodal
MMMU
81.7%
Community preference
Arena Elo (Text)
1476
Community preference (code)
Arena Elo (Code)
1419
Overview
CompanyOpenAIQwen
Release dateDec 11 2025Apr 16 2026
AccessProprietaryOpen Weight

Which is better: GPT-5.2 or Qwen3.6?

GPT-5.2 leads Qwen3.6 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). GPT-5.2 shipped 126 days before Qwen3.6, so benchmark comparisons should account for the intervening progress.

GPT-5.2 is proprietary, while Qwen3.6 is open weight.

On SWE-Bench Verified, GPT-5.2 leads at 80% vs Qwen3.6 at 73.4%. On GPQA Diamond, GPT-5.2 leads at 92.4% vs Qwen3.6 at 86%.

Frequently asked questions

GPT-5.2 was released by OpenAI on Dec 11 2025.

Qwen3.6 was released by Qwen on Apr 16 2026.

GPT-5.2 leads on SWE-Bench Verified — GPT-5.2 80% vs Qwen3.6 73.4%.

GPT-5.2 leads on GPQA Diamond — GPT-5.2 92.4% vs Qwen3.6 86%.

GPT-5.2 is a proprietary model released by OpenAI. Qwen3.6 is an open weight model released by Qwen.

Other comparisons