OpenAI trails current Humanity’s Last Exam leaderboards, with its strongest GPT-5.6 variants scoring around 47-57% while Anthropic’s Claude models (Fable 5, Mythos Preview) hold top spots near 53-65%. The 2,500-question expert benchmark, released in 2025 by the Center for AI Safety and Scale AI, tests graduate-level knowledge across math, sciences, and humanities and has proven resistant to rapid gains beyond agentic techniques like OpenAI’s earlier Deep Research system. Traders focus on OpenAI’s history of iterative releases, substantial compute resources, and potential 2026 model launches or fine-tuning advances that could close the gap, balanced against sustained competition from Anthropic and Google DeepMind. Key catalysts include any major GPT updates or benchmark-specific optimizations before year-end resolution.
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50%以上
49%
55%以上
50%
60%+
16%
65% 以上
29%
70%以上
8%
$1,729 交易量
50%以上
49%
55%以上
50%
60%+
16%
65% 以上
29%
70%以上
8%
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, 6:53 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...OpenAI trails current Humanity’s Last Exam leaderboards, with its strongest GPT-5.6 variants scoring around 47-57% while Anthropic’s Claude models (Fable 5, Mythos Preview) hold top spots near 53-65%. The 2,500-question expert benchmark, released in 2025 by the Center for AI Safety and Scale AI, tests graduate-level knowledge across math, sciences, and humanities and has proven resistant to rapid gains beyond agentic techniques like OpenAI’s earlier Deep Research system. Traders focus on OpenAI’s history of iterative releases, substantial compute resources, and potential 2026 model launches or fine-tuning advances that could close the gap, balanced against sustained competition from Anthropic and Google DeepMind. Key catalysts include any major GPT updates or benchmark-specific optimizations before year-end resolution.
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