Anthropic’s Claude 5 family, particularly Fable 5.1 and Opus 5, currently leads Humanity’s Last Exam leaderboards with scores in the 59–65% range on text-only and tool-augmented evaluations, driven by advances in multi-step reasoning and agentic scaffolding. OpenAI’s GPT-6 Astra and Meta’s Muse Spark series trail closely at 54–62%, while Google, DeepSeek, and others post lower figures on the 2,500-question expert benchmark designed to resist saturation. Recent September 2026 releases and iterative improvements have narrowed gaps among frontier labs, with trader sentiment reflecting expectations of further gains from new model launches, extended context, and tool integration before year-end. Key catalysts include upcoming developer conferences, additional Claude or GPT variants, and official leaderboard updates that could shift the highest achievable score.
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$66,702 交易量
2026-12-31
60%+
57%
65%以上
29%
70% 以上
17%
75%以上
11%
80％以上
8%
90%+
5%
$66,702 交易量
60%+
$36,244 交易量
57%
65%以上
$16,559 交易量
29%
70% 以上
$6,221 交易量
17%
75%以上
$3,596 交易量
11%
80％以上
$1,638 交易量
8%
90%+
$2,445 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 5 family, particularly Fable 5.1 and Opus 5, currently leads Humanity’s Last Exam leaderboards with scores in the 59–65% range on text-only and tool-augmented evaluations, driven by advances in multi-step reasoning and agentic scaffolding. OpenAI’s GPT-6 Astra and Meta’s Muse Spark series trail closely at 54–62%, while Google, DeepSeek, and others post lower figures on the 2,500-question expert benchmark designed to resist saturation. Recent September 2026 releases and iterative improvements have narrowed gaps among frontier labs, with trader sentiment reflecting expectations of further gains from new model launches, extended context, and tool integration before year-end. Key catalysts include upcoming developer conferences, additional Claude or GPT variants, and official leaderboard updates that could shift the highest achievable score.
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
$66,702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 5 family, particularly Fable 5.1 and Opus 5, currently leads Humanity’s Last Exam leaderboards with scores in the 59–65% range on text-only and tool-augmented evaluations, driven by advances in multi-step reasoning and agentic scaffolding. OpenAI’s GPT-6 Astra and Meta’s Muse Spark series trail closely at 54–62%, while Google, DeepSeek, and others post lower figures on the 2,500-question expert benchmark designed to resist saturation. Recent September 2026 releases and iterative improvements have narrowed gaps among frontier labs, with trader sentiment reflecting expectations of further gains from new model launches, extended context, and tool integration before year-end. Key catalysts include upcoming developer conferences, additional Claude or GPT variants, and official leaderboard updates that could shift the highest achievable score.
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
$66,702結束日期
2027-01-01市場開放時間
Jul 23, 2026, 6:41 PM ETAnthropic’s Claude 5 family, particularly Fable 5.1 and Opus 5, currently leads Humanity’s Last Exam leaderboards with scores in the 59–65% range on text-only and tool-augmented evaluations, driven by advances in multi-step reasoning and agentic scaffolding. OpenAI’s GPT-6 Astra and Meta’s Muse Spark series trail closely at 54–62%, while Google, DeepSeek, and others post lower figures on the 2,500-question expert benchmark designed to resist saturation. Recent September 2026 releases and iterative improvements have narrowed gaps among frontier labs, with trader sentiment reflecting expectations of further gains from new model launches, extended context, and tool integration before year-end. Key catalysts include upcoming developer conferences, additional Claude or GPT variants, and official leaderboard updates that could shift the highest achievable score.
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