# GPT-6.1 Sol vs GPT-6 Sol

As of Oct 15, 2026, GPT-6.1 Sol leads GPT-6 Sol in 10 of 10 shared categories: General LLM, Reasoning, Science, Coding, Coding › Agentic, Coding › Web dev, Long context, Vision, Factuality, and Abstraction (ARC).

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

GPT-6 Sol: $4.000000000000001 per 1M blended tokens.

GPT-6.1 Sol: closed weights.

GPT-6 Sol: closed weights.

- Which to pick, General LLM: As of Oct 15, 2026, GPT-6.1 Sol leads GPT-6 Sol in General LLM at #18 against #54.
- Which to pick, Reasoning: As of Oct 15, 2026, GPT-6.1 Sol leads GPT-6 Sol in Reasoning at #15 against #49.
- Which to pick, Science: As of Oct 15, 2026, GPT-6.1 Sol leads GPT-6 Sol in Science at #4 against #8.
- Which to pick, Coding: As of Oct 15, 2026, GPT-6.1 Sol leads GPT-6 Sol in Coding at #2 against #5.
- Which to pick, Coding › Agentic: As of Oct 15, 2026, GPT-6.1 Sol leads GPT-6 Sol in Coding › Agentic at #2 against #5.
- Which to pick, Coding › Web dev: As of Oct 15, 2026, GPT-6.1 Sol leads GPT-6 Sol in Coding › Web dev at #4 against #7.
- Which to pick, Long context: As of Oct 15, 2026, GPT-6.1 Sol leads GPT-6 Sol in Long context at #18 against #57.
- Which to pick, Vision: As of Oct 15, 2026, GPT-6.1 Sol leads GPT-6 Sol in Vision at #1 against #9.
- Which to pick, Factuality: As of Oct 15, 2026, GPT-6.1 Sol leads GPT-6 Sol in Factuality at #33 against #88.
- Which to pick, Abstraction (ARC): As of Oct 15, 2026, GPT-6.1 Sol leads GPT-6 Sol in Abstraction (ARC) at #1 against #6.

As of Oct 15, 2026, GPT-6.1 Sol is tied for state of the art in Vision (since Sep 30, 2026; sources GDP.pdf; methodology v1.0).

As of Oct 15, 2026, GPT-6 Sol is ranked #5 in Coding (since Oct 15, 2026; sources Terminal-Bench 4.0; methodology v1.0).