OpenAI’s current top reported HLE scores sit at 54.7–58.7% on models such as GPT-5.4 Pro and GPT-6 Astra, trailing Anthropic’s Claude Fable 5.1 and Opus 5 variants that lead public leaderboards at 59–65% as of early September 2026. Rapid gains on the 2,500-question expert-level benchmark—created by the Center for AI Safety and Scale AI to resist saturation—have come from extended reasoning modes, tool use, and iterative releases, yet OpenAI remains behind in the latest verified results. Trader consensus prices a 50%+ threshold at 95% implied probability and 55%+ at 83%, reflecting confidence that further OpenAI scaling or agentic improvements could close the gap before year-end, while 60%+ sits near even odds amid uncertainty over release timing and competitive responses. Key catalysts include any new GPT-family or Astra updates, developer conferences, or benchmark revisions through December 31, 2026.
Експериментальне резюме, згенероване ШІ з посиланням на дані Polymarket. Це не торгова порада і не впливає на вирішення цього ринку. · ОновленоHighest OpenAI score on Humanity’s Last Exam in 2026?
Highest OpenAI score on Humanity’s Last Exam in 2026?
$76,741 Обс.
Dec 31, 2026
50%+
90%
55%+
78%
60%+
38%
65%+
19%
70%+
11%
$76,741 Обс.
50%+
$12,199 Обс.
90%
55%+
$29,260 Обс.
78%
60%+
$25,322 Обс.
38%
65%+
$5,491 Обс.
19%
70%+
$4,469 Обс.
11%
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 current top reported HLE scores sit at 54.7–58.7% on models such as GPT-5.4 Pro and GPT-6 Astra, trailing Anthropic’s Claude Fable 5.1 and Opus 5 variants that lead public leaderboards at 59–65% as of early September 2026. Rapid gains on the 2,500-question expert-level benchmark—created by the Center for AI Safety and Scale AI to resist saturation—have come from extended reasoning modes, tool use, and iterative releases, yet OpenAI remains behind in the latest verified results. Trader consensus prices a 50%+ threshold at 95% implied probability and 55%+ at 83%, reflecting confidence that further OpenAI scaling or agentic improvements could close the gap before year-end, while 60%+ sits near even odds amid uncertainty over release timing and competitive responses. Key catalysts include any new GPT-family or Astra updates, developer conferences, or benchmark revisions through December 31, 2026.
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".
Ринок відкрито: Jul 23, 2026, 6:53 PM ET
Обсяг
$76,741Дата завершення
Jan 1, 2027Ринок відкрито
Jul 23, 2026, 6:53 PM ETВирішувач
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 current top reported HLE scores sit at 54.7–58.7% on models such as GPT-5.4 Pro and GPT-6 Astra, trailing Anthropic’s Claude Fable 5.1 and Opus 5 variants that lead public leaderboards at 59–65% as of early September 2026. Rapid gains on the 2,500-question expert-level benchmark—created by the Center for AI Safety and Scale AI to resist saturation—have come from extended reasoning modes, tool use, and iterative releases, yet OpenAI remains behind in the latest verified results. Trader consensus prices a 50%+ threshold at 95% implied probability and 55%+ at 83%, reflecting confidence that further OpenAI scaling or agentic improvements could close the gap before year-end, while 60%+ sits near even odds amid uncertainty over release timing and competitive responses. Key catalysts include any new GPT-family or Astra updates, developer conferences, or benchmark revisions through December 31, 2026.
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".
Обсяг
$76,741Дата завершення
Jan 1, 2027Ринок відкрито
Jul 23, 2026, 6:53 PM ETВирішувач
0x65070BE91...OpenAI’s current top reported HLE scores sit at 54.7–58.7% on models such as GPT-5.4 Pro and GPT-6 Astra, trailing Anthropic’s Claude Fable 5.1 and Opus 5 variants that lead public leaderboards at 59–65% as of early September 2026. Rapid gains on the 2,500-question expert-level benchmark—created by the Center for AI Safety and Scale AI to resist saturation—have come from extended reasoning modes, tool use, and iterative releases, yet OpenAI remains behind in the latest verified results. Trader consensus prices a 50%+ threshold at 95% implied probability and 55%+ at 83%, reflecting confidence that further OpenAI scaling or agentic improvements could close the gap before year-end, while 60%+ sits near even odds amid uncertainty over release timing and competitive responses. Key catalysts include any new GPT-family or Astra updates, developer conferences, or benchmark revisions through December 31, 2026.
Експериментальне резюме, згенероване ШІ з посиланням на дані Polymarket. Це не торгова порада і не впливає на вирішення цього ринку. · Оновлено
Обережно з зовнішніми посиланнями.
Обережно з зовнішніми посиланнями.
Часті запитання