Anthropic’s Claude Fable 5.1 and Opus 5 currently lead Humanity’s Last Exam (HLE) at 65% and 64.7%, respectively, on the 2,500-question expert-level benchmark covering math, sciences, and humanities. These gains stem from scaled reasoning training, adaptive tool use, and larger context windows that outperform earlier 2025 frontier models stuck below 20%. Meta’s Muse Spark 1.1 sits near 62%, while OpenAI and Google entries trail in the mid-to-high 50s, reflecting differences in post-training and agentic scaffolding. With three months left in 2026, new releases, verified no-tools evaluations, and multimodal extensions could lift the frontier further, though self-reported results and benchmark revisions introduce uncertainty around final resolution.
基于Polymarket数据的AI实验性摘要。这不是交易建议，也不影响该市场的结算方式。 · 更新于$53,627 交易量
2026-12-31
60%+
66%
65%+
32%
70%+
17%
75%以上
12%
80%以上
7%
90%以上
4%
$53,627 交易量
60%+
$28,525 交易量
66%
65%+
$13,622 交易量
32%
70%+
$5,265 交易量
17%
75%以上
$2,857 交易量
12%
80%以上
$1,151 交易量
7%
90%以上
$2,206 交易量
4%
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 and Opus 5 currently lead Humanity’s Last Exam (HLE) at 65% and 64.7%, respectively, on the 2,500-question expert-level benchmark covering math, sciences, and humanities. These gains stem from scaled reasoning training, adaptive tool use, and larger context windows that outperform earlier 2025 frontier models stuck below 20%. Meta’s Muse Spark 1.1 sits near 62%, while OpenAI and Google entries trail in the mid-to-high 50s, reflecting differences in post-training and agentic scaffolding. With three months left in 2026, new releases, verified no-tools evaluations, and multimodal extensions could lift the frontier further, though self-reported results and benchmark revisions introduce uncertainty around final resolution.
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".
市场开放时间： Jul 23, 2026, 6:41 PM ET
交易量
$53,627结束日期
2027-01-01市场开放时间
Jul 23, 2026, 6:41 PM ETThis 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 and Opus 5 currently lead Humanity’s Last Exam (HLE) at 65% and 64.7%, respectively, on the 2,500-question expert-level benchmark covering math, sciences, and humanities. These gains stem from scaled reasoning training, adaptive tool use, and larger context windows that outperform earlier 2025 frontier models stuck below 20%. Meta’s Muse Spark 1.1 sits near 62%, while OpenAI and Google entries trail in the mid-to-high 50s, reflecting differences in post-training and agentic scaffolding. With three months left in 2026, new releases, verified no-tools evaluations, and multimodal extensions could lift the frontier further, though self-reported results and benchmark revisions introduce uncertainty around final resolution.
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".
交易量
$53,627结束日期
2027-01-01市场开放时间
Jul 23, 2026, 6:41 PM ETAnthropic’s Claude Fable 5.1 and Opus 5 currently lead Humanity’s Last Exam (HLE) at 65% and 64.7%, respectively, on the 2,500-question expert-level benchmark covering math, sciences, and humanities. These gains stem from scaled reasoning training, adaptive tool use, and larger context windows that outperform earlier 2025 frontier models stuck below 20%. Meta’s Muse Spark 1.1 sits near 62%, while OpenAI and Google entries trail in the mid-to-high 50s, reflecting differences in post-training and agentic scaffolding. With three months left in 2026, new releases, verified no-tools evaluations, and multimodal extensions could lift the frontier further, though self-reported results and benchmark revisions introduce uncertainty around final resolution.
基于Polymarket数据的AI实验性摘要。这不是交易建议，也不影响该市场的结算方式。 · 更新于
警惕外部链接哦。
警惕外部链接哦。
常见问题