Anthropic’s Claude Fable 5.1 currently leads Humanity’s Last Exam leaderboards at 59–65% depending on the evaluation setup, ahead of Claude Opus 5 and OpenAI’s GPT-6 Astra. The 2,500-question benchmark, built to resist saturation with expert-level problems across disciplines, has seen frontier scores climb rapidly through improved reasoning scaffolds, tool use, and adaptive techniques. Meta’s Muse Spark series and Google’s Gemini previews sit a few points behind, reflecting tight competition among labs releasing iterative frontier models. With three months remaining in 2026, additional releases, higher-effort inference configurations, and ensemble methods could lift the year-end maximum, while the benchmark’s design keeps absolute gains incremental. Traders monitor official Scale and Artificial Analysis snapshots for resolution signals.
基於Polymarket數據的AI實驗性摘要。這不是交易建議，也不影響該市場的結算方式。 · 更新於$75,822 交易量
2026-12-31
60%+
48%
65%以上
29%
70% 以上
15%
75%以上
13%
80％以上
7%
90%+
5%
$75,822 交易量
60%+
$44,851 交易量
48%
65%以上
$16,633 交易量
29%
70% 以上
$6,488 交易量
15%
75%以上
$3,674 交易量
13%
80％以上
$1,710 交易量
7%
90%+
$2,465 交易量
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 Humanity’s Last Exam leaderboards at 59–65% depending on the evaluation setup, ahead of Claude Opus 5 and OpenAI’s GPT-6 Astra. The 2,500-question benchmark, built to resist saturation with expert-level problems across disciplines, has seen frontier scores climb rapidly through improved reasoning scaffolds, tool use, and adaptive techniques. Meta’s Muse Spark series and Google’s Gemini previews sit a few points behind, reflecting tight competition among labs releasing iterative frontier models. With three months remaining in 2026, additional releases, higher-effort inference configurations, and ensemble methods could lift the year-end maximum, while the benchmark’s design keeps absolute gains incremental. Traders monitor official Scale and Artificial Analysis snapshots for resolution signals.
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".
市場開放時間： Jul 23, 2026, 6:41 PM ET
交易量
$75,822結束日期
2027-01-01市場開放時間
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 currently leads Humanity’s Last Exam leaderboards at 59–65% depending on the evaluation setup, ahead of Claude Opus 5 and OpenAI’s GPT-6 Astra. The 2,500-question benchmark, built to resist saturation with expert-level problems across disciplines, has seen frontier scores climb rapidly through improved reasoning scaffolds, tool use, and adaptive techniques. Meta’s Muse Spark series and Google’s Gemini previews sit a few points behind, reflecting tight competition among labs releasing iterative frontier models. With three months remaining in 2026, additional releases, higher-effort inference configurations, and ensemble methods could lift the year-end maximum, while the benchmark’s design keeps absolute gains incremental. Traders monitor official Scale and Artificial Analysis snapshots for resolution signals.
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
$75,822結束日期
2027-01-01市場開放時間
Jul 23, 2026, 6:41 PM ETAnthropic’s Claude Fable 5.1 currently leads Humanity’s Last Exam leaderboards at 59–65% depending on the evaluation setup, ahead of Claude Opus 5 and OpenAI’s GPT-6 Astra. The 2,500-question benchmark, built to resist saturation with expert-level problems across disciplines, has seen frontier scores climb rapidly through improved reasoning scaffolds, tool use, and adaptive techniques. Meta’s Muse Spark series and Google’s Gemini previews sit a few points behind, reflecting tight competition among labs releasing iterative frontier models. With three months remaining in 2026, additional releases, higher-effort inference configurations, and ensemble methods could lift the year-end maximum, while the benchmark’s design keeps absolute gains incremental. Traders monitor official Scale and Artificial Analysis snapshots for resolution signals.
基於Polymarket數據的AI實驗性摘要。這不是交易建議，也不影響該市場的結算方式。 · 更新於
警惕外部連結哦。
警惕外部連結哦。
Frequently Asked Questions