GPT-5.4 Pro vs GPT-6 Luna
As of Oct 15, 2026, GPT-5.4 Pro leads GPT-6 Luna in 2 of 2 shared categories: Science and Abstraction (ARC).
GPT-5.4 Pro
It used to be. Was SOTA in Math.
GPT-6 Luna
Yes. Yes on Coding (best per dollar); Coding › Agentic (best per dollar). Not the overall leader.
| Category | GPT-5.4 Pro | GPT-6 Luna |
|---|---|---|
| General LLM | — | #82 · #82 in General LLM Margin 43.61702127659574 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 | #76 · #76 in Reasoning Margin 40.95744680851064 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #6 · Was SOTA · Math Margin 11.111111111111114 Epoch AI benchmarking hub · Mar 5, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Science | #6 · #6 in Science Margin — Epoch AI benchmarking hub · Mar 5, 2026 | #33 · #33 in Science Margin — Epoch AI benchmarking hub · Sep 22, 2026 |
| Coding | — | #17 · #17 in Coding Margin 81.81818181818181 Terminal-Bench Harbor Hub · Oct 6, 2026 |
| Coding › Agentic | — | #17 · #17 in Coding › Agentic Margin 81.81818181818181 Terminal-Bench Harbor Hub · Oct 6, 2026 |
| Coding › Web dev | — | #31 · #31 in Coding › Web dev Margin 24 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | — | #75 · #75 in Long context Margin 39.89361702127659 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | — | #17 · #17 in Vision Margin 47.36842105263158 Epoch AI benchmarking hub · Sep 22, 2026 |
| Factuality | #— · Not enough data Margin — Epoch AI benchmarking hub · Mar 5, 2026 | #45 · #45 in Factuality Margin 26.74418604651163 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #8 · #8 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Mar 5, 2026 | #22 · #22 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Sep 22, 2026 |
GPT-5.4 Pro: $67.5 per 1M blended tokens.
GPT-6 Luna: $0.19999999999999998 per 1M blended tokens.
GPT-5.4 Pro: closed weights.
GPT-6 Luna: closed weights.
Science: As of Oct 15, 2026, GPT-5.4 Pro leads GPT-6 Luna in Science at #6 against #33.
Abstraction (ARC): As of Oct 15, 2026, GPT-5.4 Pro leads GPT-6 Luna in Abstraction (ARC) at #8 against #22.
GPT-5.4 Pro or GPT-6 Luna?
As of Oct 15, 2026, GPT-5.4 Pro leads GPT-6 Luna in 2 of 2 shared categories: Science and Abstraction (ARC).
GPT-5.4 Pro or GPT-6 Luna for Science?
As of Oct 15, 2026, GPT-5.4 Pro leads GPT-6 Luna in Science at #6 against #33.
GPT-5.4 Pro or GPT-6 Luna for Abstraction (ARC)?
As of Oct 15, 2026, GPT-5.4 Pro leads GPT-6 Luna in Abstraction (ARC) at #8 against #22.