OpenAI’s GPT-5.4 Pro and GPT-5.5 variants have already posted 43–44.3% accuracy on Humanity’s Last Exam, a 2,500-question benchmark of expert-level problems across math, science, and the humanities created to resist rapid saturation. These results, achieved through March and April 2026, reflect continued scaling, improved reasoning chains, and targeted post-training that closed much of the gap with Google’s leading Gemini 3.1 Pro Preview. Traders are watching for any June release or high-compute run that could push an official GPT model past the next performance threshold before the 30 June cutoff, while noting that benchmark gains often arrive in uneven bursts rather than steady linear progress.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated$23,124 Vol.
Jun 30, 2026
50%+
27%
$23,124 Vol.
50%+
$23,124 Vol.
27%
This market will resolve to "Yes" if the Humanity’s Last Exam leaderboard lists any OpenAI GPT model with a score of at least the specified score by June 30, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No".
The resolution source will be the official Humanity’s Last Exam leaderboard https://scale.com/leaderboard/humanitys_last_exam.OpenAI’s GPT-5.4 Pro and GPT-5.5 variants have already posted 43–44.3% accuracy on Humanity’s Last Exam, a 2,500-question benchmark of expert-level problems across math, science, and the humanities created to resist rapid saturation. These results, achieved through March and April 2026, reflect continued scaling, improved reasoning chains, and targeted post-training that closed much of the gap with Google’s leading Gemini 3.1 Pro Preview. Traders are watching for any June release or high-compute run that could push an official GPT model past the next performance threshold before the 30 June cutoff, while noting that benchmark gains often arrive in uneven bursts rather than steady linear progress.
This market will resolve to "Yes" if the Humanity’s Last Exam leaderboard lists any OpenAI GPT model with a score of at least the specified score by June 30, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No".
The resolution source will be the official Humanity’s Last Exam leaderboard https://scale.com/leaderboard/humanitys_last_exam.
The resolution source will be the official Humanity’s Last Exam leaderboard https://scale.com/leaderboard/humanitys_last_exam.
Market Opened: Jan 30, 2026, 12:00 AM ET
Volume
$23,124End Date
Jun 30, 2026Market Opened
Jan 30, 2026, 12:00 AM ETResolver
0x65070BE91...This market will resolve to "Yes" if the Humanity’s Last Exam leaderboard lists any OpenAI GPT model with a score of at least the specified score by June 30, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No".
The resolution source will be the official Humanity’s Last Exam leaderboard https://scale.com/leaderboard/humanitys_last_exam.OpenAI’s GPT-5.4 Pro and GPT-5.5 variants have already posted 43–44.3% accuracy on Humanity’s Last Exam, a 2,500-question benchmark of expert-level problems across math, science, and the humanities created to resist rapid saturation. These results, achieved through March and April 2026, reflect continued scaling, improved reasoning chains, and targeted post-training that closed much of the gap with Google’s leading Gemini 3.1 Pro Preview. Traders are watching for any June release or high-compute run that could push an official GPT model past the next performance threshold before the 30 June cutoff, while noting that benchmark gains often arrive in uneven bursts rather than steady linear progress.
This market will resolve to "Yes" if the Humanity’s Last Exam leaderboard lists any OpenAI GPT model with a score of at least the specified score by June 30, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No".
The resolution source will be the official Humanity’s Last Exam leaderboard https://scale.com/leaderboard/humanitys_last_exam.
The resolution source will be the official Humanity’s Last Exam leaderboard https://scale.com/leaderboard/humanitys_last_exam.
Volume
$23,124End Date
Jun 30, 2026Market Opened
Jan 30, 2026, 12:00 AM ETResolver
0x65070BE91...OpenAI’s GPT-5.4 Pro and GPT-5.5 variants have already posted 43–44.3% accuracy on Humanity’s Last Exam, a 2,500-question benchmark of expert-level problems across math, science, and the humanities created to resist rapid saturation. These results, achieved through March and April 2026, reflect continued scaling, improved reasoning chains, and targeted post-training that closed much of the gap with Google’s leading Gemini 3.1 Pro Preview. Traders are watching for any June release or high-compute run that could push an official GPT model past the next performance threshold before the 30 June cutoff, while noting that benchmark gains often arrive in uneven bursts rather than steady linear progress.
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