DeepSeek V4 Flash 0731 vs GPT-5.4 Pro
As of Oct 15, 2026, DeepSeek V4 Flash 0731 leads GPT-5.4 Pro in 0 of 2 shared categories.
DeepSeek V4 Flash 0731
#18 Best recorded rank: #18 in Abstraction (ARC), as of Oct 15, 2026.
GPT-5.4 Pro
It used to be. Was SOTA in Math.
| Category | DeepSeek V4 Flash 0731 | GPT-5.4 Pro |
|---|---|---|
| Reasoning | #— · Not enough data Margin — Epoch AI benchmarking hub · Jul 31, 2026 | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Math | — | #6 · Was SOTA · Math Margin 11.111111111111114 Epoch AI benchmarking hub · Mar 5, 2026 |
| Science | #27 · #27 in Science Margin — Epoch AI benchmarking hub · Jul 31, 2026 | #6 · #6 in Science Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Factuality | #— · Not enough data Margin — Epoch AI benchmarking hub · Jul 31, 2026 | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Abstraction (ARC) | #18 · #18 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Jul 31, 2026 | #8 · #8 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
DeepSeek V4 Flash 0731: $0.17200000000000001 per 1M blended tokens.
GPT-5.4 Pro: $67.5 per 1M blended tokens.
DeepSeek V4 Flash 0731: closed weights.
GPT-5.4 Pro: closed weights.
Science: As of Oct 15, 2026, GPT-5.4 Pro leads DeepSeek V4 Flash 0731 in Science at #6 against #27.
Abstraction (ARC): As of Oct 15, 2026, GPT-5.4 Pro leads DeepSeek V4 Flash 0731 in Abstraction (ARC) at #8 against #18.
DeepSeek V4 Flash 0731 · GPT-5.4 Pro
DeepSeek V4 Flash 0731 or GPT-5.4 Pro?
As of Oct 15, 2026, DeepSeek V4 Flash 0731 leads GPT-5.4 Pro in 0 of 2 shared categories.
DeepSeek V4 Flash 0731 or GPT-5.4 Pro for Science?
As of Oct 15, 2026, GPT-5.4 Pro leads DeepSeek V4 Flash 0731 in Science at #6 against #27.
DeepSeek V4 Flash 0731 or GPT-5.4 Pro for Abstraction (ARC)?
As of Oct 15, 2026, GPT-5.4 Pro leads DeepSeek V4 Flash 0731 in Abstraction (ARC) at #8 against #18.