# Claude Haiku 5.5 vs GPT-6.1 Sol

As of Oct 15, 2026, Claude Haiku 5.5 leads GPT-6.1 Sol in 0 of 2 shared categories.

Claude Haiku 5.5: $0.19999999999999998 per 1M blended tokens.

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

Claude Haiku 5.5: closed weights.

GPT-6.1 Sol: closed weights.

- Which to pick, Science: As of Oct 15, 2026, GPT-6.1 Sol leads Claude Haiku 5.5 in Science at #4 against #38.
- Which to pick, Coding › Web dev: As of Oct 15, 2026, GPT-6.1 Sol leads Claude Haiku 5.5 in Coding › Web dev at #4 against #28.

As of Oct 15, 2026, Claude Haiku 5.5 is state of the art on best per dollar in Math (since Oct 14, 2026; sources Humanity's Last Exam; methodology v1.0).

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).