Anthropic’s Claude variants currently dominate Humanity’s Last Exam leaderboards, with Claude Fable 5.1 posting the highest published scores around 59-65% as of mid-September 2026, ahead of other Claude releases and competitors from OpenAI and Google. Rapid gains stem from iterative advances in reasoning, tool use, and adaptive scaffolding on the 2,500-question expert benchmark spanning math, physics, biology, and humanities. Recent internal data shows Claude models now lead or collaborate on over 90% of Anthropic’s R&D tasks, accelerating model improvements. With several months remaining in 2026, additional frontier releases or refined evaluation protocols could lift the top Claude score further before year-end resolution.
Polymarketデータを参照したAI生成の実験的な要約。これは取引アドバイスではなく、このマーケットの解決方法には一切関係ありません。 · 更新日$109,568 Vol.
55%以上
92%
60%以上
41%
65%以上
19%
70%以上
12%
75%以上
5%
$109,568 Vol.
55%以上
92%
60%以上
41%
65%以上
19%
70%以上
12%
75%以上
5%
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".
マーケット開始日: Jul 23, 2026, 6:42 PM ET
結算ソース
https://agi.safe.ai/リゾルバー
0x65070BE91...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".
結算ソース
https://agi.safe.ai/リゾルバー
0x65070BE91...Anthropic’s Claude variants currently dominate Humanity’s Last Exam leaderboards, with Claude Fable 5.1 posting the highest published scores around 59-65% as of mid-September 2026, ahead of other Claude releases and competitors from OpenAI and Google. Rapid gains stem from iterative advances in reasoning, tool use, and adaptive scaffolding on the 2,500-question expert benchmark spanning math, physics, biology, and humanities. Recent internal data shows Claude models now lead or collaborate on over 90% of Anthropic’s R&D tasks, accelerating model improvements. With several months remaining in 2026, additional frontier releases or refined evaluation protocols could lift the top Claude score further before year-end resolution.
Polymarketデータを参照したAI生成の実験的な要約。これは取引アドバイスではなく、このマーケットの解決方法には一切関係ありません。 · 更新日



外部リンクに注意してください。
外部リンクに注意してください。
よくある質問