GPT-5.5 vs GPT-6 Luna
As of Oct 14, 2026, GPT-5.5 leads GPT-6 Luna in 7 of 8 shared categories: General LLM, Reasoning, Science, Long context, Vision, Factuality, and Abstraction (ARC).
GPT-5.5
It used to be. Was SOTA in General LLM.
GPT-6 Luna
Yes. Yes on Coding (best per dollar); Coding › Agentic (best per dollar). Not the overall leader.
| Category | GPT-5.5 | GPT-6 Luna |
|---|---|---|
| General LLM | #21 · Was SOTA · General LLM Margin 14.285714285714292 LMArena leaderboard dataset · Oct 13, 2026 | #65 · #65 in General LLM Margin 44.21768707482993 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #25 · #25 in Reasoning Margin 17.808219178082197 LMArena leaderboard dataset · Oct 13, 2026 | #61 · #61 in Reasoning Margin 42.465753424657535 LMArena leaderboard dataset · Oct 13, 2026 |
| Math | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 |
| Science | #30 · #30 in Science Margin — Epoch AI benchmarking hub · Apr 23, 2026 | #33 · #33 in Science Margin — Epoch AI benchmarking hub · Sep 22, 2026 |
| Coding | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #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 | #44 · #44 in Coding › Web dev Margin 40.18691588785047 LMArena leaderboard dataset · Oct 13, 2026 | #29 · #29 in Coding › Web dev Margin 26.168224299065415 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | #23 · Was SOTA · Long context Margin 15.646258503401356 LMArena leaderboard dataset · Oct 13, 2026 | #61 · #61 in Long context Margin 41.49659863945578 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #10 · Was SOTA · Vision Margin 28.94736842105263 Epoch AI benchmarking hub · Apr 23, 2026 | #17 · #17 in Vision Margin 47.36842105263158 Epoch AI benchmarking hub · Sep 22, 2026 |
| Factuality | #5 · Was SOTA · Factuality Margin 4.477611940298502 LMArena leaderboard dataset · Oct 13, 2026 | #39 · #39 in Factuality Margin 29.85074626865672 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #7 · #7 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Apr 23, 2026 | #22 · #22 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Sep 22, 2026 |
GPT-5.5: $11.25 per 1M blended tokens.
GPT-6 Luna: $0.19999999999999998 per 1M blended tokens.
GPT-5.5: closed weights.
GPT-6 Luna: closed weights.
General LLM: As of Oct 14, 2026, GPT-5.5 leads GPT-6 Luna in General LLM at #21 against #65.
Reasoning: As of Oct 14, 2026, GPT-5.5 leads GPT-6 Luna in Reasoning at #25 against #61.
Science: As of Oct 14, 2026, GPT-5.5 leads GPT-6 Luna in Science at #30 against #33.
Coding › Web dev: As of Oct 14, 2026, GPT-6 Luna leads GPT-5.5 in Coding › Web dev at #29 against #44.
Long context: As of Oct 14, 2026, GPT-5.5 leads GPT-6 Luna in Long context at #23 against #61.
Vision: As of Oct 14, 2026, GPT-5.5 leads GPT-6 Luna in Vision at #10 against #17.
Factuality: As of Oct 14, 2026, GPT-5.5 leads GPT-6 Luna in Factuality at #5 against #39.
Abstraction (ARC): As of Oct 14, 2026, GPT-5.5 leads GPT-6 Luna in Abstraction (ARC) at #7 against #22.
GPT-5.5 or GPT-6 Luna?
As of Oct 14, 2026, GPT-5.5 leads GPT-6 Luna in 7 of 8 shared categories: General LLM, Reasoning, Science, Long context, Vision, Factuality, and Abstraction (ARC).
GPT-5.5 or GPT-6 Luna for General LLM?
As of Oct 14, 2026, GPT-5.5 leads GPT-6 Luna in General LLM at #21 against #65.
GPT-5.5 or GPT-6 Luna for Reasoning?
As of Oct 14, 2026, GPT-5.5 leads GPT-6 Luna in Reasoning at #25 against #61.
GPT-5.5 or GPT-6 Luna for Science?
As of Oct 14, 2026, GPT-5.5 leads GPT-6 Luna in Science at #30 against #33.