DeepSeek R1 0528 vs GPT-5.4 Pro
As of Oct 14, 2026, DeepSeek R1 0528 leads GPT-5.4 Pro in 0 of 2 shared categories.
DeepSeek R1 0528
It used to be. Was SOTA in General LLM.
GPT-5.4 Pro
It used to be. Was SOTA in Math.
| Category | DeepSeek R1 0528 | GPT-5.4 Pro |
|---|---|---|
| General LLM | #92 · #92 in General LLM Margin 62.585034013605444 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Reasoning | #98 · #98 in Reasoning Margin 67.8082191780822 LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Math | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #6 · Was SOTA · Math Margin 11.111111111111114 Epoch AI benchmarking hub · Mar 5, 2026 |
| Science | #78 · #78 in Science Margin — Epoch AI benchmarking hub · May 28, 2025 | #6 · #6 in Science Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Coding | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | — |
| Long context | #114 · #114 in Long context Margin 77.55102040816327 LMArena leaderboard dataset · Oct 13, 2026 | — |
| Factuality | — | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
| Abstraction (ARC) | #70 · #70 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · May 28, 2025 | #8 · #8 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Mar 5, 2026 |
DeepSeek R1 0528: $0.9125000000000001 per 1M blended tokens.
GPT-5.4 Pro: $67.5 per 1M blended tokens.
DeepSeek R1 0528: open weights.
GPT-5.4 Pro: closed weights.
Science: As of Oct 14, 2026, GPT-5.4 Pro leads DeepSeek R1 0528 in Science at #6 against #78.
Abstraction (ARC): As of Oct 14, 2026, GPT-5.4 Pro leads DeepSeek R1 0528 in Abstraction (ARC) at #8 against #70.
DeepSeek R1 0528 · GPT-5.4 Pro
DeepSeek R1 0528 or GPT-5.4 Pro?
As of Oct 14, 2026, DeepSeek R1 0528 leads GPT-5.4 Pro in 0 of 2 shared categories.
DeepSeek R1 0528 or GPT-5.4 Pro for Science?
As of Oct 14, 2026, GPT-5.4 Pro leads DeepSeek R1 0528 in Science at #6 against #78.
DeepSeek R1 0528 or GPT-5.4 Pro for Abstraction (ARC)?
As of Oct 14, 2026, GPT-5.4 Pro leads DeepSeek R1 0528 in Abstraction (ARC) at #8 against #70.