Anthropic's Claude Fable 5.1 and Opus 5 variants currently lead public HLE leaderboards at 59–65% accuracy on the 2,500-question expert-crafted benchmark, ahead of OpenAI's GPT-6 Astra and GPT-5.4 Pro near 55% and Meta's Muse Spark 1.1 around 62%. Rapid gains since the January 2025 release—driven by scaled reasoning chains, tool integration, and targeted post-training—have outpaced initial projections, with frontier models advancing from single-digit scores to the mid-60s in under 20 months. Key near-term catalysts include anticipated late-2026 releases from Anthropic, OpenAI, and Google DeepMind, plus HLE-Rolling updates that could alter evaluation conditions before year-end resolution. Trader sentiment reflects this momentum tempered by uncertainty over whether any lab will breach 70% on the closed-ended graduate-level questions by December 31.
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$64,860 交易量
2026-12-31
60%+
59%
65%以上
29%
70% 以上
16%
75%以上
13%
80％以上
7%
90%+
5%
$64,860 交易量
60%+
$35,947 交易量
59%
65%以上
$16,107 交易量
29%
70% 以上
$5,879 交易量
16%
75%以上
$3,571 交易量
13%
80％以上
$1,151 交易量
7%
90%+
$2,206 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 and Opus 5 variants currently lead public HLE leaderboards at 59–65% accuracy on the 2,500-question expert-crafted benchmark, ahead of OpenAI's GPT-6 Astra and GPT-5.4 Pro near 55% and Meta's Muse Spark 1.1 around 62%. Rapid gains since the January 2025 release—driven by scaled reasoning chains, tool integration, and targeted post-training—have outpaced initial projections, with frontier models advancing from single-digit scores to the mid-60s in under 20 months. Key near-term catalysts include anticipated late-2026 releases from Anthropic, OpenAI, and Google DeepMind, plus HLE-Rolling updates that could alter evaluation conditions before year-end resolution. Trader sentiment reflects this momentum tempered by uncertainty over whether any lab will breach 70% on the closed-ended graduate-level questions by December 31.
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
$64,860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 and Opus 5 variants currently lead public HLE leaderboards at 59–65% accuracy on the 2,500-question expert-crafted benchmark, ahead of OpenAI's GPT-6 Astra and GPT-5.4 Pro near 55% and Meta's Muse Spark 1.1 around 62%. Rapid gains since the January 2025 release—driven by scaled reasoning chains, tool integration, and targeted post-training—have outpaced initial projections, with frontier models advancing from single-digit scores to the mid-60s in under 20 months. Key near-term catalysts include anticipated late-2026 releases from Anthropic, OpenAI, and Google DeepMind, plus HLE-Rolling updates that could alter evaluation conditions before year-end resolution. Trader sentiment reflects this momentum tempered by uncertainty over whether any lab will breach 70% on the closed-ended graduate-level questions by December 31.
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
$64,860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 and Opus 5 variants currently lead public HLE leaderboards at 59–65% accuracy on the 2,500-question expert-crafted benchmark, ahead of OpenAI's GPT-6 Astra and GPT-5.4 Pro near 55% and Meta's Muse Spark 1.1 around 62%. Rapid gains since the January 2025 release—driven by scaled reasoning chains, tool integration, and targeted post-training—have outpaced initial projections, with frontier models advancing from single-digit scores to the mid-60s in under 20 months. Key near-term catalysts include anticipated late-2026 releases from Anthropic, OpenAI, and Google DeepMind, plus HLE-Rolling updates that could alter evaluation conditions before year-end resolution. Trader sentiment reflects this momentum tempered by uncertainty over whether any lab will breach 70% on the closed-ended graduate-level questions by December 31.
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