OpenAI’s recent GPT-6 Astra release and iterative GPT-5.4/5.5 Pro updates have driven trader confidence that the company will clear 50–55% on Humanity’s Last Exam by year-end, even as Anthropic’s Claude Fable 5.1 and Opus 5 models currently lead leaderboards at 59–65%. The 2,500-question expert benchmark emphasizes graduate-level reasoning across mathematics, physics, biology, and multimodal tasks, where Anthropic’s adaptive scaffolding and tool integration have produced a measurable edge. OpenAI trails at 54.7–58.7% on reported runs but continues to close the gap through enhanced chain-of-thought and agentic workflows. With four months remaining, any new flagship launch, major reasoning upgrade, or benchmark protocol shift could alter the 55%+ and 60%+ thresholds that currently sit at 83% and 53% implied probability.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated$76,783 Vol.
Dec 31, 2026
50%+
90%
55%+
78%
60%+
38%
65%+
19%
70%+
12%
$76,783 Vol.
50%+
$12,241 Vol.
90%
55%+
$29,260 Vol.
78%
60%+
$25,322 Vol.
38%
65%+
$5,491 Vol.
19%
70%+
$4,469 Vol.
12%
This market will resolve to "Yes" if any model published by OpenAI achieves at least the specified accuracy on Humanity’s Last Exam by December 31, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No".
For resolution, “accuracy” refers solely to the value labeled “HLE Accuracy” or a clear equivalent metric if the data’s presentation or terminology is restructured, regardless of the model’s Calibration Error or any other displayed metric.
The resolution source will be the official Humanity’s Last Exam leaderboard at https://agi.safe.ai/. If the resolution source becomes unavailable during the listed timeframe, this market will remain open to allow the relevant data to become available again. If the source remains unavailable after the end of the listed timeframe or is otherwise confirmed to be permanently unavailable, official Humanity’s Last Exam results published elsewhere may be used. If no official alternative source is available, this market will resolve to "No".OpenAI’s recent GPT-6 Astra release and iterative GPT-5.4/5.5 Pro updates have driven trader confidence that the company will clear 50–55% on Humanity’s Last Exam by year-end, even as Anthropic’s Claude Fable 5.1 and Opus 5 models currently lead leaderboards at 59–65%. The 2,500-question expert benchmark emphasizes graduate-level reasoning across mathematics, physics, biology, and multimodal tasks, where Anthropic’s adaptive scaffolding and tool integration have produced a measurable edge. OpenAI trails at 54.7–58.7% on reported runs but continues to close the gap through enhanced chain-of-thought and agentic workflows. With four months remaining, any new flagship launch, major reasoning upgrade, or benchmark protocol shift could alter the 55%+ and 60%+ thresholds that currently sit at 83% and 53% implied probability.
This market will resolve to "Yes" if any model published by OpenAI achieves at least the specified accuracy on Humanity’s Last Exam by December 31, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No".
For resolution, “accuracy” refers solely to the value labeled “HLE Accuracy” or a clear equivalent metric if the data’s presentation or terminology is restructured, regardless of the model’s Calibration Error or any other displayed metric.
The resolution source will be the official Humanity’s Last Exam leaderboard at https://agi.safe.ai/. If the resolution source becomes unavailable during the listed timeframe, this market will remain open to allow the relevant data to become available again. If the source remains unavailable after the end of the listed timeframe or is otherwise confirmed to be permanently unavailable, official Humanity’s Last Exam results published elsewhere may be used. If no official alternative source is available, this market will resolve to "No".
For resolution, “accuracy” refers solely to the value labeled “HLE Accuracy” or a clear equivalent metric if the data’s presentation or terminology is restructured, regardless of the model’s Calibration Error or any other displayed metric.
The resolution source will be the official Humanity’s Last Exam leaderboard at https://agi.safe.ai/. If the resolution source becomes unavailable during the listed timeframe, this market will remain open to allow the relevant data to become available again. If the source remains unavailable after the end of the listed timeframe or is otherwise confirmed to be permanently unavailable, official Humanity’s Last Exam results published elsewhere may be used. If no official alternative source is available, this market will resolve to "No".
Market Opened: Jul 23, 2026, 6:53 PM ET
Volume
$76,783End Date
Jan 1, 2027Market Opened
Jul 23, 2026, 6:53 PM ETResolver
0x65070BE91...This market will resolve to "Yes" if any model published by OpenAI achieves at least the specified accuracy on Humanity’s Last Exam by December 31, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No".
For resolution, “accuracy” refers solely to the value labeled “HLE Accuracy” or a clear equivalent metric if the data’s presentation or terminology is restructured, regardless of the model’s Calibration Error or any other displayed metric.
The resolution source will be the official Humanity’s Last Exam leaderboard at https://agi.safe.ai/. If the resolution source becomes unavailable during the listed timeframe, this market will remain open to allow the relevant data to become available again. If the source remains unavailable after the end of the listed timeframe or is otherwise confirmed to be permanently unavailable, official Humanity’s Last Exam results published elsewhere may be used. If no official alternative source is available, this market will resolve to "No".OpenAI’s recent GPT-6 Astra release and iterative GPT-5.4/5.5 Pro updates have driven trader confidence that the company will clear 50–55% on Humanity’s Last Exam by year-end, even as Anthropic’s Claude Fable 5.1 and Opus 5 models currently lead leaderboards at 59–65%. The 2,500-question expert benchmark emphasizes graduate-level reasoning across mathematics, physics, biology, and multimodal tasks, where Anthropic’s adaptive scaffolding and tool integration have produced a measurable edge. OpenAI trails at 54.7–58.7% on reported runs but continues to close the gap through enhanced chain-of-thought and agentic workflows. With four months remaining, any new flagship launch, major reasoning upgrade, or benchmark protocol shift could alter the 55%+ and 60%+ thresholds that currently sit at 83% and 53% implied probability.
This market will resolve to "Yes" if any model published by OpenAI achieves at least the specified accuracy on Humanity’s Last Exam by December 31, 2026, 11:59 PM ET. Otherwise, this market will resolve to "No".
For resolution, “accuracy” refers solely to the value labeled “HLE Accuracy” or a clear equivalent metric if the data’s presentation or terminology is restructured, regardless of the model’s Calibration Error or any other displayed metric.
The resolution source will be the official Humanity’s Last Exam leaderboard at https://agi.safe.ai/. If the resolution source becomes unavailable during the listed timeframe, this market will remain open to allow the relevant data to become available again. If the source remains unavailable after the end of the listed timeframe or is otherwise confirmed to be permanently unavailable, official Humanity’s Last Exam results published elsewhere may be used. If no official alternative source is available, this market will resolve to "No".
For resolution, “accuracy” refers solely to the value labeled “HLE Accuracy” or a clear equivalent metric if the data’s presentation or terminology is restructured, regardless of the model’s Calibration Error or any other displayed metric.
The resolution source will be the official Humanity’s Last Exam leaderboard at https://agi.safe.ai/. If the resolution source becomes unavailable during the listed timeframe, this market will remain open to allow the relevant data to become available again. If the source remains unavailable after the end of the listed timeframe or is otherwise confirmed to be permanently unavailable, official Humanity’s Last Exam results published elsewhere may be used. If no official alternative source is available, this market will resolve to "No".
Volume
$76,783End Date
Jan 1, 2027Market Opened
Jul 23, 2026, 6:53 PM ETResolver
0x65070BE91...OpenAI’s recent GPT-6 Astra release and iterative GPT-5.4/5.5 Pro updates have driven trader confidence that the company will clear 50–55% on Humanity’s Last Exam by year-end, even as Anthropic’s Claude Fable 5.1 and Opus 5 models currently lead leaderboards at 59–65%. The 2,500-question expert benchmark emphasizes graduate-level reasoning across mathematics, physics, biology, and multimodal tasks, where Anthropic’s adaptive scaffolding and tool integration have produced a measurable edge. OpenAI trails at 54.7–58.7% on reported runs but continues to close the gap through enhanced chain-of-thought and agentic workflows. With four months remaining, any new flagship launch, major reasoning upgrade, or benchmark protocol shift could alter the 55%+ and 60%+ thresholds that currently sit at 83% and 53% implied probability.
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