GPT-5.4 Nano vs GPT-6.1 Sol
As of Oct 14, 2026, GPT-5.4 Nano leads GPT-6.1 Sol in 0 of 6 shared categories.
GPT-5.4 Nano
#43 Best recorded rank: #43 in Abstraction (ARC), as of Oct 14, 2026.
GPT-6.1 Sol
Yes. SOTA in co-SOTA in Vision.
| Category | GPT-5.4 Nano | GPT-6.1 Sol |
|---|---|---|
| General LLM | #114 · #114 in General LLM Margin 77.55102040816327 LMArena leaderboard dataset · Oct 13, 2026 | #18 · #18 in General LLM Margin 12.244897959183675 LMArena leaderboard dataset · Oct 13, 2026 |
| Reasoning | #109 · #109 in Reasoning Margin 75.34246575342466 LMArena leaderboard dataset · Oct 13, 2026 | #15 · #15 in Reasoning Margin 10.958904109589042 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 | #73 · #73 in Science Margin — Epoch AI benchmarking hub · Mar 17, 2026 | #4 · #4 in Science Margin — Epoch AI benchmarking hub · Sep 29, 2026 |
| Coding | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 13, 2026 | #2 · Near-SOTA · Coding Margin 13.63636363636364 Terminal-Bench Harbor Hub · Oct 6, 2026 |
| Coding › Agentic | — | #2 · Near-SOTA · Coding › Agentic Margin 13.63636363636364 Terminal-Bench Harbor Hub · Oct 6, 2026 |
| Coding › Web dev | — | #4 · Near-SOTA · Coding › Web dev Margin 2.803738317757009 LMArena leaderboard dataset · Oct 13, 2026 |
| Long context | #120 · #120 in Long context Margin 81.63265306122449 LMArena leaderboard dataset · Oct 13, 2026 | #17 · #17 in Long context Margin 11.564625850340136 LMArena leaderboard dataset · Oct 13, 2026 |
| Vision | #— · Not enough data Margin — LMArena leaderboard dataset · Oct 9, 2026 | #1 · Co-SOTA · Vision Margin 0 Epoch AI benchmarking hub · Sep 29, 2026 |
| Factuality | #98 · #98 in Factuality Margin 73.88059701492537 LMArena leaderboard dataset · Oct 13, 2026 | #29 · #29 in Factuality Margin 22.388059701492537 LMArena leaderboard dataset · Oct 13, 2026 |
| Abstraction (ARC) | #43 · #43 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Mar 17, 2026 | #1 · #1 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Sep 29, 2026 |
GPT-5.4 Nano: $0.4625 per 1M blended tokens.
GPT-6.1 Sol: $4.000000000000001 per 1M blended tokens.
GPT-5.4 Nano: closed weights.
GPT-6.1 Sol: closed weights.
General LLM: As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5.4 Nano in General LLM at #18 against #114.
Reasoning: As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5.4 Nano in Reasoning at #15 against #109.
Science: As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5.4 Nano in Science at #4 against #73.
Long context: As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5.4 Nano in Long context at #17 against #120.
Factuality: As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5.4 Nano in Factuality at #29 against #98.
Abstraction (ARC): As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5.4 Nano in Abstraction (ARC) at #1 against #43.
GPT-5.4 Nano or GPT-6.1 Sol?
As of Oct 14, 2026, GPT-5.4 Nano leads GPT-6.1 Sol in 0 of 6 shared categories.
GPT-5.4 Nano or GPT-6.1 Sol for General LLM?
As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5.4 Nano in General LLM at #18 against #114.
GPT-5.4 Nano or GPT-6.1 Sol for Reasoning?
As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5.4 Nano in Reasoning at #15 against #109.
GPT-5.4 Nano or GPT-6.1 Sol for Science?
As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5.4 Nano in Science at #4 against #73.