DeepSeek V4 Pro 0813 vs GPT-5.5
As of Oct 15, 2026, DeepSeek V4 Pro 0813 leads GPT-5.5 in 1 of 2 shared categories: Science.
DeepSeek V4 Pro 0813
#15 Best recorded rank: #15 in Abstraction (ARC), as of Oct 15, 2026.
GPT-5.5
Close. Near-SOTA in Factuality, rank #5.
| Category | DeepSeek V4 Pro 0813 | GPT-5.5 |
|---|---|---|
| General LLM | — | #22 · Was SOTA · General LLM Margin 11.702127659574472 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #— · Not enough data Margin — Epoch AI benchmarking hub · Aug 13, 2026 | #26 · #26 in Reasoning Margin 14.36170212765957 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | — | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Science | #24 · #24 in Science Margin — Epoch AI benchmarking hub · Aug 13, 2026 | #30 · #30 in Science Margin — Epoch AI benchmarking hub · Apr 23, 2026 |
| Coding | — | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Coding › Web dev | — | #48 · #48 in Coding › Web dev Margin 37.6 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | — | #26 · Was SOTA · Long context Margin 13.829787234042556 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | — | #10 · Was SOTA · Vision Margin 28.94736842105263 Epoch AI benchmarking hub · Apr 23, 2026 |
| Factuality | #— · Not enough data Margin — Epoch AI benchmarking hub · Aug 13, 2026 | #5 · Near-SOTA · Factuality Margin 3.4883720930232442 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #15 · #15 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Aug 13, 2026 | #7 · #7 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Apr 23, 2026 |
DeepSeek V4 Pro 0813: $0.9900000000000001 per 1M blended tokens.
GPT-5.5: $11.25 per 1M blended tokens.
DeepSeek V4 Pro 0813: closed weights.
GPT-5.5: closed weights.
Science: As of Oct 15, 2026, DeepSeek V4 Pro 0813 leads GPT-5.5 in Science at #24 against #30.
Abstraction (ARC): As of Oct 15, 2026, GPT-5.5 leads DeepSeek V4 Pro 0813 in Abstraction (ARC) at #7 against #15.
DeepSeek V4 Pro 0813 · GPT-5.5
DeepSeek V4 Pro 0813 or GPT-5.5?
As of Oct 15, 2026, DeepSeek V4 Pro 0813 leads GPT-5.5 in 1 of 2 shared categories: Science.
DeepSeek V4 Pro 0813 or GPT-5.5 for Science?
As of Oct 15, 2026, DeepSeek V4 Pro 0813 leads GPT-5.5 in Science at #24 against #30.
DeepSeek V4 Pro 0813 or GPT-5.5 for Abstraction (ARC)?
As of Oct 15, 2026, GPT-5.5 leads DeepSeek V4 Pro 0813 in Abstraction (ARC) at #7 against #15.