Recent progress in large language models has produced multiple gold-medal and perfect 42/42 scores on the official IMO 2026 problems released after the July contest in Shanghai, including officially graded perfect results from Huawei’s Celia and Xiaohongshu models plus independent verified runs by Claude Fable 5, GPT-5.6 Sol, and others. Open-weight systems such as DeepSeek V4 Flash have also cleared the 29-point gold threshold at very low cost. These advances explain why traders view frontier AI reasoning capabilities as having surpassed the required level. However, the market prices “No” at 74.5% because no AI has entered or been awarded a medal in the actual human-only IMO, and organizational rules plus the 2026 calendar leave little room for an official entry before year-end.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated$10,341 Vol.
$10,341 Vol.
$10,341 Vol.
$10,341 Vol.
The resolution source is the IMO Grand Challenge (https://imo-grand-challenge.github.io/) and the Artificial Intelligence Math Olympiad (AIMO, https://aimoprize.com/). If either source demonstrates that an AI has won the challenge/prize before the resolution date, this market will resolve to "Yes".
Market Opened: Nov 12, 2025, 5:08 PM ET
Resolver
0x65070BE91...The resolution source is the IMO Grand Challenge (https://imo-grand-challenge.github.io/) and the Artificial Intelligence Math Olympiad (AIMO, https://aimoprize.com/). If either source demonstrates that an AI has won the challenge/prize before the resolution date, this market will resolve to "Yes".
Resolver
0x65070BE91...Recent progress in large language models has produced multiple gold-medal and perfect 42/42 scores on the official IMO 2026 problems released after the July contest in Shanghai, including officially graded perfect results from Huawei’s Celia and Xiaohongshu models plus independent verified runs by Claude Fable 5, GPT-5.6 Sol, and others. Open-weight systems such as DeepSeek V4 Flash have also cleared the 29-point gold threshold at very low cost. These advances explain why traders view frontier AI reasoning capabilities as having surpassed the required level. However, the market prices “No” at 74.5% because no AI has entered or been awarded a medal in the actual human-only IMO, and organizational rules plus the 2026 calendar leave little room for an official entry before year-end.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated


Beware of external links.
Beware of external links.
Frequently Asked Questions