Anthropic’s Claude Fable 5.1 currently leads multiple Humanity’s Last Exam leaderboards with scores near 59-65% under varied reasoning configurations, ahead of Claude Opus 5 and OpenAI’s GPT-6 Astra. This reflects rapid gains in chain-of-thought scaffolding, adaptive reasoning, and model scale since the benchmark’s 2025 launch, when frontier systems scored in the single digits. Anthropic’s consistent top placements stem from targeted improvements in expert-level knowledge and multi-step reasoning across the 2,500-question set spanning math, sciences, and humanities. Competitive pressure from Google Gemini variants, Meta’s Muse Spark, and OpenAI’s iterative GPT releases continues to narrow gaps, while the benchmark’s deliberate difficulty and periodic HLE-Rolling updates keep the frontier dynamic through late 2026.
Экспериментальная сводка, созданная ИИ на основе данных Polymarket. Это не является торговой рекомендацией и не влияет на то, как разрешается этот рынок. · ОбновленоСамый высокий балл на последнем экзамене человечества в 2026 году?
Самый высокий балл на последнем экзамене человечества в 2026 году?
$72,512 Объем
31 дек. 2026 г.
60%+
42%
65%+
29%
70%+
14%
75%+
13%
80%+
7%
90%+
5%
$72,512 Объем
60%+
$41,544 Объем
42%
65%+
$16,633 Объем
29%
70%+
$6,485 Объем
14%
75%+
$3,674 Объем
13%
80%+
$1,710 Объем
7%
90%+
$2,465 Объем
5%
This market will resolve to "Yes" if any model 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 currently leads multiple Humanity’s Last Exam leaderboards with scores near 59-65% under varied reasoning configurations, ahead of Claude Opus 5 and OpenAI’s GPT-6 Astra. This reflects rapid gains in chain-of-thought scaffolding, adaptive reasoning, and model scale since the benchmark’s 2025 launch, when frontier systems scored in the single digits. Anthropic’s consistent top placements stem from targeted improvements in expert-level knowledge and multi-step reasoning across the 2,500-question set spanning math, sciences, and humanities. Competitive pressure from Google Gemini variants, Meta’s Muse Spark, and OpenAI’s iterative GPT releases continues to narrow gaps, while the benchmark’s deliberate difficulty and periodic HLE-Rolling updates keep the frontier dynamic through late 2026.
This market will resolve to "Yes" if any model 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".
Открытие рынка: Jul 23, 2026, 6:41 PM ET
Объем
$72,512Дата окончания
1 янв. 2027 г.Открытие рынка
Jul 23, 2026, 6:41 PM ETИсточник определения исхода
https://agi.safe.ai/Кто определяет исход
0x65070BE91...This market will resolve to "Yes" if any model 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 currently leads multiple Humanity’s Last Exam leaderboards with scores near 59-65% under varied reasoning configurations, ahead of Claude Opus 5 and OpenAI’s GPT-6 Astra. This reflects rapid gains in chain-of-thought scaffolding, adaptive reasoning, and model scale since the benchmark’s 2025 launch, when frontier systems scored in the single digits. Anthropic’s consistent top placements stem from targeted improvements in expert-level knowledge and multi-step reasoning across the 2,500-question set spanning math, sciences, and humanities. Competitive pressure from Google Gemini variants, Meta’s Muse Spark, and OpenAI’s iterative GPT releases continues to narrow gaps, while the benchmark’s deliberate difficulty and periodic HLE-Rolling updates keep the frontier dynamic through late 2026.
This market will resolve to "Yes" if any model 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".
Объем
$72,512Дата окончания
1 янв. 2027 г.Открытие рынка
Jul 23, 2026, 6:41 PM ETИсточник определения исхода
https://agi.safe.ai/Кто определяет исход
0x65070BE91...Anthropic’s Claude Fable 5.1 currently leads multiple Humanity’s Last Exam leaderboards with scores near 59-65% under varied reasoning configurations, ahead of Claude Opus 5 and OpenAI’s GPT-6 Astra. This reflects rapid gains in chain-of-thought scaffolding, adaptive reasoning, and model scale since the benchmark’s 2025 launch, when frontier systems scored in the single digits. Anthropic’s consistent top placements stem from targeted improvements in expert-level knowledge and multi-step reasoning across the 2,500-question set spanning math, sciences, and humanities. Competitive pressure from Google Gemini variants, Meta’s Muse Spark, and OpenAI’s iterative GPT releases continues to narrow gaps, while the benchmark’s deliberate difficulty and periodic HLE-Rolling updates keep the frontier dynamic through late 2026.
Экспериментальная сводка, созданная ИИ на основе данных Polymarket. Это не является торговой рекомендацией и не влияет на то, как разрешается этот рынок. · ОбновленоСвязанные
Достигнет ли максимальный балл, набранный моделью OpenAI на Последнем Экзамене Человечества в 2026 году, 55% или больше?
77%
Да
Будет ли наивысший балл, набранный моделью Meta на Humanity’s Last Exam в 2026 году, 60% или выше?
18%
Да
Даст ли любая модель Anthropic Claude результат 55% или выше на Humanity’s Last Exam в 2026 году?
93%
Да
Не доверяй внешним ссылкам.
Не доверяй внешним ссылкам.
Часто задаваемые вопросы