DeepSeek-V4-Flash vs GPT-5.4
DeepSeek vs OpenAI — benchmarks, pricing, and capabilities side by side.
- •DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 74.9)
- •DeepSeek-V4-Flash is cheaper ($0.10 vs $2.50 per 1M input)
- •DeepSeek-V4-Flash is faster
- •GPT-5.4 has a larger context window (1.1M)
| DeepSeek-V4-Flash | GPT-5.4 | |
|---|---|---|
| Intelligence index | 89.4 | 74.9 |
| Developer | DeepSeek | OpenAI |
| Type | LLM | LLM |
| Access | Open weights | API only |
| Context window | 1,048,576 tokens | 1,050,000 tokens |
| Input price | $0.10 / 1M | $2.50 / 1M |
| Output price | $0.20 / 1M | $15.00 / 1M |
| Speed | 109 tok/s | 84 tok/s |
| Released | April 24, 2026 | March 5, 2026 |
| Parameters | 284B (13B active) | — |
| Input modalities | Text | Text, Image |
| Output modalities | Text | Text |
Shared benchmarks
DeepSeek-V4-Flash
GPT-5.4
GPQA Diamond
89.4
92
Humanity’s Last Exam
32.1
41.6