GPT-5.6 Outperforms Claude Fable 5 on FrontierMath Tier 4?
8
Ṁ100Ṁ221Dec 31
59%
chance
1H
6H
1D
1W
1M
ALL
Resolves to the next GPT model released regardless of number. Only the “stock” GPT counts, so no mini, nano, pro, codex, etc
Update 2026-06-26 (PST) (AI summary of creator comment): The model "Sol" will count as the relevant GPT model for this market, as its pricing is comparable to GPT-5.5.
This question is managed and resolved by Manifold.
Market context
Get 
1,000 to start trading!
1,000