DeepSeek-V3.2vsQwen3.7-Max

DeepSeek-V3.2
Qwen3.7-Max
Benchmarks
Nonsense detection
BullshitBench v2
13%
71%Best
Agentic coding
SWE-Bench Pro
60.6%
Agentic terminal coding
Terminal-Bench 2.0
69.7%
Multi-step tool use
MCP Atlas
76.4%
Science
GPQA Diamond
92.4%
Community preference (code)
Arena Elo (Code)
1361
Overview
CompanyDeepSeekQwen
Release dateDec 1 2025May 20 2026
AccessOpen WeightProprietary

Which is better: DeepSeek-V3.2 or Qwen3.7-Max?

Qwen3.7-Max leads DeepSeek-V3.2 on 1 of the 1 benchmark they both report (BullshitBench v2). DeepSeek-V3.2 shipped 170 days before Qwen3.7-Max, so benchmark comparisons should account for the intervening progress.

DeepSeek-V3.2 is open weight, while Qwen3.7-Max is proprietary.

On BullshitBench v2, Qwen3.7-Max leads at 71% vs DeepSeek-V3.2 at 13%.

Frequently asked questions

DeepSeek-V3.2 was released by DeepSeek on Dec 1 2025.

Qwen3.7-Max was released by Qwen on May 20 2026.

DeepSeek-V3.2 is an open weight model released by DeepSeek. Qwen3.7-Max is a proprietary model released by Qwen.

Other comparisons