Anthropic’s Claude Fable 5.1 and Opus 5 currently lead public HLE leaderboards at 59–65% on tool-augmented and high-effort runs, while OpenAI’s GPT-6 Astra trails at 54.7–57.2% depending on the exact configuration and whether tools are allowed. Scores have risen rapidly since the benchmark’s early-2025 launch—from single digits to the mid-50s range—driven by stronger chain-of-thought reasoning, larger context windows, and agentic tool use, though the text-only frontier still sits in the mid-40s percent. OpenAI’s GPT-5 and GPT-6 series releases have narrowed gaps on math and science subsets, yet Anthropic maintains an edge on calibration and multidisciplinary questions. Traders will monitor OpenAI’s next major model drop, any announced HLE-specific fine-tunes, and whether tool-augmented protocols become the resolution standard 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$107,820 Vol.
Dec 31, 2026
55%+
78%
60%+
33%
65%+
16%
70%+
10%
$107,820 Vol.
55%+
$34,352 Vol.
78%
60%+
$41,192 Vol.
33%
65%+
$9,431 Vol.
16%
70%+
$5,516 Vol.
10%
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".Anthropic’s Claude Fable 5.1 and Opus 5 currently lead public HLE leaderboards at 59–65% on tool-augmented and high-effort runs, while OpenAI’s GPT-6 Astra trails at 54.7–57.2% depending on the exact configuration and whether tools are allowed. Scores have risen rapidly since the benchmark’s early-2025 launch—from single digits to the mid-50s range—driven by stronger chain-of-thought reasoning, larger context windows, and agentic tool use, though the text-only frontier still sits in the mid-40s percent. OpenAI’s GPT-5 and GPT-6 series releases have narrowed gaps on math and science subsets, yet Anthropic maintains an edge on calibration and multidisciplinary questions. Traders will monitor OpenAI’s next major model drop, any announced HLE-specific fine-tunes, and whether tool-augmented protocols become the resolution standard before year-end.
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
$107,820End 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".Anthropic’s Claude Fable 5.1 and Opus 5 currently lead public HLE leaderboards at 59–65% on tool-augmented and high-effort runs, while OpenAI’s GPT-6 Astra trails at 54.7–57.2% depending on the exact configuration and whether tools are allowed. Scores have risen rapidly since the benchmark’s early-2025 launch—from single digits to the mid-50s range—driven by stronger chain-of-thought reasoning, larger context windows, and agentic tool use, though the text-only frontier still sits in the mid-40s percent. OpenAI’s GPT-5 and GPT-6 series releases have narrowed gaps on math and science subsets, yet Anthropic maintains an edge on calibration and multidisciplinary questions. Traders will monitor OpenAI’s next major model drop, any announced HLE-specific fine-tunes, and whether tool-augmented protocols become the resolution standard before year-end.
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
$107,820End Date
Jan 1, 2027Market Opened
Jul 23, 2026, 6:53 PM ETResolver
0x65070BE91...Anthropic’s Claude Fable 5.1 and Opus 5 currently lead public HLE leaderboards at 59–65% on tool-augmented and high-effort runs, while OpenAI’s GPT-6 Astra trails at 54.7–57.2% depending on the exact configuration and whether tools are allowed. Scores have risen rapidly since the benchmark’s early-2025 launch—from single digits to the mid-50s range—driven by stronger chain-of-thought reasoning, larger context windows, and agentic tool use, though the text-only frontier still sits in the mid-40s percent. OpenAI’s GPT-5 and GPT-6 series releases have narrowed gaps on math and science subsets, yet Anthropic maintains an edge on calibration and multidisciplinary questions. Traders will monitor OpenAI’s next major model drop, any announced HLE-specific fine-tunes, and whether tool-augmented protocols become the resolution standard 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