DeepSeek-V3.2 vs GPT-5
DeepSeek DeepSeek-V3.2 | OpenAI GPT-5 | |
|---|---|---|
| Overview | ||
| Company | DeepSeek | OpenAI |
| Release date | Dec 1 2025 | Aug 7 2025 |
| Access | Open Weight | Proprietary |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 13% | 21%Best |
Community preference (code) Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | — | 1394 |
| Timeline | ||
| Release gap | GPT-5 shipped 116 days before DeepSeek-V3.2 | |
Which is better: DeepSeek-V3.2 or GPT-5?
GPT-5 leads DeepSeek-V3.2 on 1 of the 1 benchmark they both report (BullshitBench v2). GPT-5 shipped 116 days before DeepSeek-V3.2, so benchmark comparisons should account for the intervening progress.
DeepSeek-V3.2 is open weight, while GPT-5 is proprietary.
On BullshitBench v2, GPT-5 leads at 21% vs DeepSeek-V3.2 at 13%.
Frequently asked questions
DeepSeek-V3.2 was released by DeepSeek on Dec 1 2025.
GPT-5 was released by OpenAI on Aug 7 2025.
DeepSeek-V3.2 is an open weight model released by DeepSeek. GPT-5 is a proprietary model released by OpenAI.
Other comparisons
DeepSeek-V3.2 vs Claude Sonnet 5GPT-5 vs Claude Sonnet 5DeepSeek-V3.2 vs Gemini OmniGPT-5 vs Gemini OmniDeepSeek-V3.2 vs Muse Spark 1.1GPT-5 vs Muse Spark 1.1DeepSeek-V3.2 vs Grok 4.5GPT-5 vs Grok 4.5DeepSeek-V3.2 vs Mistral Medium 3.5GPT-5 vs Mistral Medium 3.5DeepSeek-V3.2 vs Kimi K2.7 CodeGPT-5 vs Kimi K2.7 Code