Anthropic’s Claude lineup leads the Humanity’s Last Exam (HLE) leaderboard as of mid-August 2026, with Claude Opus 5 and Claude Mythos 5 posting the top reported scores near 64.7% (with tools) and Claude Fable 5 at 55.5% on independent trackers. The benchmark’s expert-level, multidisciplinary questions have seen rapid gains from single-digit results in 2025 as Anthropic iterated through Opus 4.6 (February), Mythos Preview (April), Opus 4.7/4.8, and the June Fable 5 / Mythos 5 releases, emphasizing extended reasoning, adaptive thinking, and tool use. These capabilities directly lift HLE performance while competitors such as GPT-5 variants and Gemini 3 trail. Traders are focused on whether further 2026 updates or higher-effort configurations can push the ceiling higher before year-end, with the market reflecting Anthropic’s consistent edge on this particular reasoning test.
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$60,210 交易量
55% 以上
86%
60% 以上
54%
65% 以上
16%
70% 以上
8%
75%+
5%
$60,210 交易量
55% 以上
86%
60% 以上
54%
65% 以上
16%
70% 以上
8%
75%+
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".
市場開放時間: Jul 23, 2026, 6:42 PM ET
Resolver
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".
Resolver
0x65070BE91...Anthropic’s Claude lineup leads the Humanity’s Last Exam (HLE) leaderboard as of mid-August 2026, with Claude Opus 5 and Claude Mythos 5 posting the top reported scores near 64.7% (with tools) and Claude Fable 5 at 55.5% on independent trackers. The benchmark’s expert-level, multidisciplinary questions have seen rapid gains from single-digit results in 2025 as Anthropic iterated through Opus 4.6 (February), Mythos Preview (April), Opus 4.7/4.8, and the June Fable 5 / Mythos 5 releases, emphasizing extended reasoning, adaptive thinking, and tool use. These capabilities directly lift HLE performance while competitors such as GPT-5 variants and Gemini 3 trail. Traders are focused on whether further 2026 updates or higher-effort configurations can push the ceiling higher before year-end, with the market reflecting Anthropic’s consistent edge on this particular reasoning test.
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