OpenAI’s current top reported HLE scores sit at 54.7–58.7% on models such as GPT-5.4 Pro and GPT-6 Astra, trailing Anthropic’s Claude Fable 5.1 and Opus 5 variants that lead public leaderboards at 59–65% as of early September 2026. Rapid gains on the 2,500-question expert-level benchmark—created by the Center for AI Safety and Scale AI to resist saturation—have come from extended reasoning modes, tool use, and iterative releases, yet OpenAI remains behind in the latest verified results. Trader consensus prices a 50%+ threshold at 95% implied probability and 55%+ at 83%, reflecting confidence that further OpenAI scaling or agentic improvements could close the gap before year-end, while 60%+ sits near even odds amid uncertainty over release timing and competitive responses. Key catalysts include any new GPT-family or Astra updates, developer conferences, or benchmark revisions through December 31, 2026.
Resumen experimental generado por IA con datos de Polymarket. Esto no es asesoramiento de trading y no influye en cómo se resuelve este mercado. · Actualizado$76,741 Vol.
31 dic 2026
50%+
90%
55% o más
78%
60% o más
38%
65% o más
19%
70% o más
11%
$76,741 Vol.
50%+
$12,199 Vol.
90%
55% o más
$29,260 Vol.
78%
60% o más
$25,322 Vol.
38%
65% o más
$5,491 Vol.
19%
70% o más
$4,469 Vol.
11%
This market will resolve to "Yes" if any model published by OpenAI 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".OpenAI’s current top reported HLE scores sit at 54.7–58.7% on models such as GPT-5.4 Pro and GPT-6 Astra, trailing Anthropic’s Claude Fable 5.1 and Opus 5 variants that lead public leaderboards at 59–65% as of early September 2026. Rapid gains on the 2,500-question expert-level benchmark—created by the Center for AI Safety and Scale AI to resist saturation—have come from extended reasoning modes, tool use, and iterative releases, yet OpenAI remains behind in the latest verified results. Trader consensus prices a 50%+ threshold at 95% implied probability and 55%+ at 83%, reflecting confidence that further OpenAI scaling or agentic improvements could close the gap before year-end, while 60%+ sits near even odds amid uncertainty over release timing and competitive responses. Key catalysts include any new GPT-family or Astra updates, developer conferences, or benchmark revisions through December 31, 2026.
This market will resolve to "Yes" if any model published by OpenAI 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".
Mercado abierto: Jul 23, 2026, 6:53 PM ET
Volumen
$76,741Fecha de finalización
1 ene 2027Mercado abierto
Jul 23, 2026, 6:53 PM ETResolver
0x65070BE91...This market will resolve to "Yes" if any model published by OpenAI 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".OpenAI’s current top reported HLE scores sit at 54.7–58.7% on models such as GPT-5.4 Pro and GPT-6 Astra, trailing Anthropic’s Claude Fable 5.1 and Opus 5 variants that lead public leaderboards at 59–65% as of early September 2026. Rapid gains on the 2,500-question expert-level benchmark—created by the Center for AI Safety and Scale AI to resist saturation—have come from extended reasoning modes, tool use, and iterative releases, yet OpenAI remains behind in the latest verified results. Trader consensus prices a 50%+ threshold at 95% implied probability and 55%+ at 83%, reflecting confidence that further OpenAI scaling or agentic improvements could close the gap before year-end, while 60%+ sits near even odds amid uncertainty over release timing and competitive responses. Key catalysts include any new GPT-family or Astra updates, developer conferences, or benchmark revisions through December 31, 2026.
This market will resolve to "Yes" if any model published by OpenAI 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".
Volumen
$76,741Fecha de finalización
1 ene 2027Mercado abierto
Jul 23, 2026, 6:53 PM ETResolver
0x65070BE91...OpenAI’s current top reported HLE scores sit at 54.7–58.7% on models such as GPT-5.4 Pro and GPT-6 Astra, trailing Anthropic’s Claude Fable 5.1 and Opus 5 variants that lead public leaderboards at 59–65% as of early September 2026. Rapid gains on the 2,500-question expert-level benchmark—created by the Center for AI Safety and Scale AI to resist saturation—have come from extended reasoning modes, tool use, and iterative releases, yet OpenAI remains behind in the latest verified results. Trader consensus prices a 50%+ threshold at 95% implied probability and 55%+ at 83%, reflecting confidence that further OpenAI scaling or agentic improvements could close the gap before year-end, while 60%+ sits near even odds amid uncertainty over release timing and competitive responses. Key catalysts include any new GPT-family or Astra updates, developer conferences, or benchmark revisions through December 31, 2026.
Resumen experimental generado por IA con datos de Polymarket. Esto no es asesoramiento de trading y no influye en cómo se resuelve este mercado. · ActualizadoRelacionado
¿Será la puntuación más alta lograda en el Último Examen de la Humanidad en 2026 del 60% o superior?
66%
Sí
¿Será la puntuación más alta alcanzada por un modelo de Meta en el Último Examen de la Humanidad en 2026 del 55% o más?
44%
Sí
¿Obtendrá un modelo Anthropic Claude una puntuación del 55% o más en el Último Examen de la Humanidad en 2026?
90%
Sí
Cuidado con los enlaces externos.
Cuidado con los enlaces externos.
Preguntas frecuentes