# GPT-5 vs GPT-6.1 Sol

As of Oct 14, 2026, GPT-5 leads GPT-6.1 Sol in 0 of 7 shared categories.

GPT-5: $3.4375000000000004 per 1M blended tokens.

GPT-6.1 Sol: $4.000000000000001 per 1M blended tokens.

GPT-5: closed weights.

GPT-6.1 Sol: closed weights.

- Which to pick, General LLM: As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5 in General LLM at #18 against #76.
- Which to pick, Reasoning: As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5 in Reasoning at #15 against #78.
- Which to pick, Science: As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5 in Science at #4 against #54.
- Which to pick, Coding › Web dev: As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5 in Coding › Web dev at #4 against #66.
- Which to pick, Long context: As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5 in Long context at #17 against #107.
- Which to pick, Factuality: As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5 in Factuality at #29 against #93.
- Which to pick, Abstraction (ARC): As of Oct 14, 2026, GPT-6.1 Sol leads GPT-5 in Abstraction (ARC) at #1 against #34.

As of Oct 14, 2026, GPT-5 is a former state-of-the-art holder in General LLM (since Aug 27, 2025; sources LMArena Text (style-controlled, overall); methodology v1.0).

As of Oct 14, 2026, GPT-6.1 Sol is tied for state of the art in Vision (since Sep 30, 2026; sources GDP.pdf; methodology v1.0).