DeepSeek-V4-Flash vs GPT-5.4 mini
DeepSeek DeepSeek-V4-Flash | OpenAI GPT-5.4 mini | |
|---|---|---|
| Overview | ||
| Company | DeepSeek | OpenAI |
| Release date | Apr 24 2026 | Mar 17 2026 |
| Access | Open Weight | Proprietary |
| Specifications | ||
Context window | — | 400k |
| 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. | 18% | 32%Best |
Competitive coding LiveCodeBenchCoding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 91.6% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 88.1% | — |
| Timeline | ||
| Release gap | GPT-5.4 mini shipped 38 days before DeepSeek-V4-Flash | |
Which is better: DeepSeek-V4-Flash or GPT-5.4 mini?
GPT-5.4 mini leads DeepSeek-V4-Flash on 1 of the 1 benchmark they both report (BullshitBench v2). GPT-5.4 mini shipped 38 days before DeepSeek-V4-Flash, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Flash is open weight, while GPT-5.4 mini is proprietary.
On BullshitBench v2, GPT-5.4 mini leads at 32% vs DeepSeek-V4-Flash at 18%.
Frequently asked questions
DeepSeek-V4-Flash was released by DeepSeek on Apr 24 2026.
GPT-5.4 mini was released by OpenAI on Mar 17 2026.
DeepSeek-V4-Flash is an open weight model released by DeepSeek. GPT-5.4 mini is a proprietary model released by OpenAI.
Other comparisons
DeepSeek-V4-Flash vs Claude Sonnet 5GPT-5.4 mini vs Claude Sonnet 5DeepSeek-V4-Flash vs Gemini 3.5 FlashGPT-5.4 mini vs Gemini 3.5 FlashDeepSeek-V4-Flash vs Muse Spark 1.1GPT-5.4 mini vs Muse Spark 1.1DeepSeek-V4-Flash vs Grok 4.5GPT-5.4 mini vs Grok 4.5DeepSeek-V4-Flash vs Mistral Medium 3.5GPT-5.4 mini vs Mistral Medium 3.5DeepSeek-V4-Flash vs Kimi K2.7 CodeGPT-5.4 mini vs Kimi K2.7 Code