Anthropic’s recent Claude Fable 5.1 release has driven current trader sentiment by posting the highest reported Humanity’s Last Exam scores, reaching 59.1% on standard leaderboards and up to 65% in tool-assisted evaluations as of mid-September 2026. This edges out prior Claude Opus 5 and Mythos 5 variants while outpacing OpenAI’s GPT-6 Astra and GPT-5.6 series along with Meta’s Muse Spark models. Progress stems from iterative gains in multi-step reasoning, extended inference compute, and tool integration on the 2,500-question expert benchmark spanning math, sciences, and humanities. With four months left in 2026, further Q4 model launches or optimizations from leading labs could lift the frontier above 60-65% thresholds, though exact resolution hinges on official leaderboard verification of published systems.
สรุปจาก AI ทดลองที่อ้างอิงข้อมูลจาก Polymarket ไม่ใช่คำแนะนำในการเทรดและไม่มีผลต่อการตัดสินตลาดนี้ · อัปเดตแล้ว$73,368 ปริมาณ
Dec 31, 2026
60%+
42%
65%+
29%
70%+
15%
75%+
13%
80%+
7%
90%+
5%
$73,368 ปริมาณ
60%+
$42,399 ปริมาณ
42%
65%+
$16,633 ปริมาณ
29%
70%+
$6,485 ปริมาณ
15%
75%+
$3,674 ปริมาณ
13%
80%+
$1,710 ปริมาณ
7%
90%+
$2,465 ปริมาณ
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 recent Claude Fable 5.1 release has driven current trader sentiment by posting the highest reported Humanity’s Last Exam scores, reaching 59.1% on standard leaderboards and up to 65% in tool-assisted evaluations as of mid-September 2026. This edges out prior Claude Opus 5 and Mythos 5 variants while outpacing OpenAI’s GPT-6 Astra and GPT-5.6 series along with Meta’s Muse Spark models. Progress stems from iterative gains in multi-step reasoning, extended inference compute, and tool integration on the 2,500-question expert benchmark spanning math, sciences, and humanities. With four months left in 2026, further Q4 model launches or optimizations from leading labs could lift the frontier above 60-65% thresholds, though exact resolution hinges on official leaderboard verification of published systems.
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".
ตลาดเปิดเมื่อ: Jul 23, 2026, 6:41 PM ET
ปริมาณการซื้อขาย
$73,368วันสิ้นสุด
Jan 1, 2027ตลาดเปิดเมื่อ
Jul 23, 2026, 6:41 PM ETแหล่งข้อมูลการตัดสินผล
https://agi.safe.ai/ผู้ตัดสินผล
0x65070BE91...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 recent Claude Fable 5.1 release has driven current trader sentiment by posting the highest reported Humanity’s Last Exam scores, reaching 59.1% on standard leaderboards and up to 65% in tool-assisted evaluations as of mid-September 2026. This edges out prior Claude Opus 5 and Mythos 5 variants while outpacing OpenAI’s GPT-6 Astra and GPT-5.6 series along with Meta’s Muse Spark models. Progress stems from iterative gains in multi-step reasoning, extended inference compute, and tool integration on the 2,500-question expert benchmark spanning math, sciences, and humanities. With four months left in 2026, further Q4 model launches or optimizations from leading labs could lift the frontier above 60-65% thresholds, though exact resolution hinges on official leaderboard verification of published systems.
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".
ปริมาณการซื้อขาย
$73,368วันสิ้นสุด
Jan 1, 2027ตลาดเปิดเมื่อ
Jul 23, 2026, 6:41 PM ETแหล่งข้อมูลการตัดสินผล
https://agi.safe.ai/ผู้ตัดสินผล
0x65070BE91...Anthropic’s recent Claude Fable 5.1 release has driven current trader sentiment by posting the highest reported Humanity’s Last Exam scores, reaching 59.1% on standard leaderboards and up to 65% in tool-assisted evaluations as of mid-September 2026. This edges out prior Claude Opus 5 and Mythos 5 variants while outpacing OpenAI’s GPT-6 Astra and GPT-5.6 series along with Meta’s Muse Spark models. Progress stems from iterative gains in multi-step reasoning, extended inference compute, and tool integration on the 2,500-question expert benchmark spanning math, sciences, and humanities. With four months left in 2026, further Q4 model launches or optimizations from leading labs could lift the frontier above 60-65% thresholds, though exact resolution hinges on official leaderboard verification of published systems.
สรุปจาก AI ทดลองที่อ้างอิงข้อมูลจาก Polymarket ไม่ใช่คำแนะนำในการเทรดและไม่มีผลต่อการตัดสินตลาดนี้ · อัปเดตแล้วที่เกี่ยวข้อง
Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 55% or higher?
77%
Will the highest score achieved by a Meta model on Humanity’s Last Exam in 2026 be 55% or higher?
26%
Will the highest score achieved by an Anthropic Claude model on Humanity’s Last Exam in 2026 be 55% or higher?
92%
ระวังลิงก์ภายนอก
ระวังลิงก์ภายนอก
คำถามที่พบบ่อย