DeepSeek-V4-ProvsQwen3.8-27B

DeepSeek-V4-Pro
Qwen3.8-27B
Specifications
Parameters
27B
Context window
262k
Benchmarks
Nonsense detection
BullshitBench v2
14%
Agentic coding
SWE-Bench Pro
61.7%
Agentic coding
DeepSWE 1.1
42.2%
Repo-level code generation
NL2Repo-Bench
42.3%
Software engineering
QwenSWEBench
79%
Competitive coding
LiveCodeBench
93.5%Best
90.3%
Agentic terminal coding
Terminal-Bench 2.1
73%
Professional tool use
JobBench
33.4%
Long-horizon office work
CoWorkBench
70.7%
Web browsing
BrowseComp
83.4%
Multidisciplinary reasoning
Humanity's Last Exam · no tools
30.8%
Science
GPQA Diamond
90.1%Best
89.2%
Instruction following
IFBench
79.5%
Agentic computer use
Agent's Last Exam · pass@1
20.4%
Agentic computer use
Agent's Last Exam · score
42.9%
Community preference
Arena Elo (Text)
1457
Community preference (code)
Arena Elo (Code)
1446
Overview
CompanyDeepSeekQwen
Release dateApr 24 2026Aug 14 2026
AccessOpen WeightOpen Weight

Which is better: DeepSeek-V4-Pro or Qwen3.8-27B?

DeepSeek-V4-Pro leads Qwen3.8-27B on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek-V4-Pro shipped 112 days before Qwen3.8-27B, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On LiveCodeBench, DeepSeek-V4-Pro leads at 93.5% vs Qwen3.8-27B at 90.3%. On GPQA Diamond, DeepSeek-V4-Pro leads at 90.1% vs Qwen3.8-27B at 89.2%.

Frequently asked questions

DeepSeek-V4-Pro was released by DeepSeek on Apr 24 2026.

Qwen3.8-27B was released by Qwen on Aug 14 2026.

DeepSeek-V4-Pro leads on LiveCodeBench — DeepSeek-V4-Pro 93.5% vs Qwen3.8-27B 90.3%.

DeepSeek-V4-Pro leads on GPQA Diamond — DeepSeek-V4-Pro 90.1% vs Qwen3.8-27B 89.2%.

Other comparisons