Anthropic’s latest Claude variants, especially Fable 5.1, currently post the highest reported scores on Humanity’s Last Exam, a 2,500-question expert-authored benchmark spanning advanced mathematics, physics, biology, and other domains designed to resist saturation. Recent September 2026 leaderboards from Artificial Analysis and BenchLM place Fable 5.1 at 59.1% (closed-book or adaptive) to 65% (tool-assisted), ahead of Claude Opus 5 and Mythos 5, with OpenAI’s GPT-6 Astra and Meta’s Muse Spark trailing several points behind. These gains stem from iterative improvements in reasoning chains, tool use, and training on frontier data, though protocol differences such as tool access or grader updates can shift exact figures. Remaining headroom on HLE and potential new Claude releases or HLE-Rolling updates before year-end keep the 2026 peak fluid for traders tracking model announcements and independent evaluations.
Експериментальне резюме, згенероване ШІ з посиланням на дані Polymarket. Це не торгова порада і не впливає на вирішення цього ринку. · ОновленоHighest Claude score on Humanity’s Last Exam in 2026?
Highest Claude score on Humanity’s Last Exam in 2026?
$107,845 Обс.
Dec 31, 2026
55%+
91%
60%+
44%
65%+
19%
70%+
13%
75%+
8%
$107,845 Обс.
55%+
$27,736 Обс.
91%
60%+
$45,818 Обс.
44%
65%+
$28,321 Обс.
19%
70%+
$4,458 Обс.
13%
75%+
$1,513 Обс.
8%
This market will resolve to "Yes" if any Anthropic Claude 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 latest Claude variants, especially Fable 5.1, currently post the highest reported scores on Humanity’s Last Exam, a 2,500-question expert-authored benchmark spanning advanced mathematics, physics, biology, and other domains designed to resist saturation. Recent September 2026 leaderboards from Artificial Analysis and BenchLM place Fable 5.1 at 59.1% (closed-book or adaptive) to 65% (tool-assisted), ahead of Claude Opus 5 and Mythos 5, with OpenAI’s GPT-6 Astra and Meta’s Muse Spark trailing several points behind. These gains stem from iterative improvements in reasoning chains, tool use, and training on frontier data, though protocol differences such as tool access or grader updates can shift exact figures. Remaining headroom on HLE and potential new Claude releases or HLE-Rolling updates before year-end keep the 2026 peak fluid for traders tracking model announcements and independent evaluations.
This market will resolve to "Yes" if any Anthropic Claude 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".
Ринок відкрито: Jul 23, 2026, 6:42 PM ET
Обсяг
$107,845Дата завершення
Jan 1, 2027Ринок відкрито
Jul 23, 2026, 6:42 PM ETДжерело вирішення
https://agi.safe.ai/Вирішувач
0x65070BE91...This market will resolve to "Yes" if any Anthropic Claude 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 latest Claude variants, especially Fable 5.1, currently post the highest reported scores on Humanity’s Last Exam, a 2,500-question expert-authored benchmark spanning advanced mathematics, physics, biology, and other domains designed to resist saturation. Recent September 2026 leaderboards from Artificial Analysis and BenchLM place Fable 5.1 at 59.1% (closed-book or adaptive) to 65% (tool-assisted), ahead of Claude Opus 5 and Mythos 5, with OpenAI’s GPT-6 Astra and Meta’s Muse Spark trailing several points behind. These gains stem from iterative improvements in reasoning chains, tool use, and training on frontier data, though protocol differences such as tool access or grader updates can shift exact figures. Remaining headroom on HLE and potential new Claude releases or HLE-Rolling updates before year-end keep the 2026 peak fluid for traders tracking model announcements and independent evaluations.
This market will resolve to "Yes" if any Anthropic Claude 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".
Обсяг
$107,845Дата завершення
Jan 1, 2027Ринок відкрито
Jul 23, 2026, 6:42 PM ETДжерело вирішення
https://agi.safe.ai/Вирішувач
0x65070BE91...Anthropic’s latest Claude variants, especially Fable 5.1, currently post the highest reported scores on Humanity’s Last Exam, a 2,500-question expert-authored benchmark spanning advanced mathematics, physics, biology, and other domains designed to resist saturation. Recent September 2026 leaderboards from Artificial Analysis and BenchLM place Fable 5.1 at 59.1% (closed-book or adaptive) to 65% (tool-assisted), ahead of Claude Opus 5 and Mythos 5, with OpenAI’s GPT-6 Astra and Meta’s Muse Spark trailing several points behind. These gains stem from iterative improvements in reasoning chains, tool use, and training on frontier data, though protocol differences such as tool access or grader updates can shift exact figures. Remaining headroom on HLE and potential new Claude releases or HLE-Rolling updates before year-end keep the 2026 peak fluid for traders tracking model announcements and independent evaluations.
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