Moonshot AI’s July 2026 release of the 2.8-trillion-parameter Kimi K3, featuring a 1-million-token context window, native multimodal support, and Stable LatentMoE architecture, has anchored trader expectations for the model’s 2026 HLE performance. Current independent evaluations place Kimi K3 at approximately 46.9% on standard HLE runs and up to 56% with tools, positioning it as the leading open-weight entry but trailing Anthropic’s Claude Fable 5.1 (59.1%) and OpenAI’s GPT-6 Astra (54.7%). Recent availability on Amazon Bedrock and incremental gains from K2.8 preview updates support continued fine-tuning and agentic optimizations through year-end. HLE’s expert-authored questions across mathematics, sciences, and humanities make further double-digit gains challenging without major new releases or scaffolding breakthroughs.
Экспериментальная сводка, созданная ИИ на основе данных Polymarket. Это не является торговой рекомендацией и не влияет на то, как разрешается этот рынок. · ОбновленоСамый высокий балл по шкале Кими на последнем экзамене человечества в 2026 году?
Самый высокий балл по шкале Кими на последнем экзамене человечества в 2026 году?
$63,365 Объем
31 дек. 2026 г.
45%+
85%
50%+
40%
55%+
19%
60%+
11%
65%+
7%
$63,365 Объем
45%+
$15,400 Объем
85%
50%+
$24,595 Объем
40%
55%+
$11,805 Объем
19%
60%+
$9,733 Объем
11%
65%+
$1,832 Объем
7%
This market will resolve to "Yes" if any Moonshot Kimi 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".Moonshot AI’s July 2026 release of the 2.8-trillion-parameter Kimi K3, featuring a 1-million-token context window, native multimodal support, and Stable LatentMoE architecture, has anchored trader expectations for the model’s 2026 HLE performance. Current independent evaluations place Kimi K3 at approximately 46.9% on standard HLE runs and up to 56% with tools, positioning it as the leading open-weight entry but trailing Anthropic’s Claude Fable 5.1 (59.1%) and OpenAI’s GPT-6 Astra (54.7%). Recent availability on Amazon Bedrock and incremental gains from K2.8 preview updates support continued fine-tuning and agentic optimizations through year-end. HLE’s expert-authored questions across mathematics, sciences, and humanities make further double-digit gains challenging without major new releases or scaffolding breakthroughs.
This market will resolve to "Yes" if any Moonshot Kimi 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".
Открытие рынка: Jul 23, 2026, 6:43 PM ET
Объем
$63,365Дата окончания
1 янв. 2027 г.Открытие рынка
Jul 23, 2026, 6:43 PM ETИсточник определения исхода
https://agi.safe.ai/Кто определяет исход
0x65070BE91...This market will resolve to "Yes" if any Moonshot Kimi 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".Moonshot AI’s July 2026 release of the 2.8-trillion-parameter Kimi K3, featuring a 1-million-token context window, native multimodal support, and Stable LatentMoE architecture, has anchored trader expectations for the model’s 2026 HLE performance. Current independent evaluations place Kimi K3 at approximately 46.9% on standard HLE runs and up to 56% with tools, positioning it as the leading open-weight entry but trailing Anthropic’s Claude Fable 5.1 (59.1%) and OpenAI’s GPT-6 Astra (54.7%). Recent availability on Amazon Bedrock and incremental gains from K2.8 preview updates support continued fine-tuning and agentic optimizations through year-end. HLE’s expert-authored questions across mathematics, sciences, and humanities make further double-digit gains challenging without major new releases or scaffolding breakthroughs.
This market will resolve to "Yes" if any Moonshot Kimi 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".
Объем
$63,365Дата окончания
1 янв. 2027 г.Открытие рынка
Jul 23, 2026, 6:43 PM ETИсточник определения исхода
https://agi.safe.ai/Кто определяет исход
0x65070BE91...Moonshot AI’s July 2026 release of the 2.8-trillion-parameter Kimi K3, featuring a 1-million-token context window, native multimodal support, and Stable LatentMoE architecture, has anchored trader expectations for the model’s 2026 HLE performance. Current independent evaluations place Kimi K3 at approximately 46.9% on standard HLE runs and up to 56% with tools, positioning it as the leading open-weight entry but trailing Anthropic’s Claude Fable 5.1 (59.1%) and OpenAI’s GPT-6 Astra (54.7%). Recent availability on Amazon Bedrock and incremental gains from K2.8 preview updates support continued fine-tuning and agentic optimizations through year-end. HLE’s expert-authored questions across mathematics, sciences, and humanities make further double-digit gains challenging without major new releases or scaffolding breakthroughs.
Экспериментальная сводка, созданная ИИ на основе данных Polymarket. Это не является торговой рекомендацией и не влияет на то, как разрешается этот рынок. · ОбновленоСвязанные
Будет ли наивысший балл, набранный на Последнем экзамене человечества в 2026 году, равен 60% или выше?
44%
Да
Достигнет ли максимальный балл, набранный моделью OpenAI на Последнем Экзамене Человечества в 2026 году, 55% или больше?
78%
Да
Будет ли максимальный результат, достигнутый моделью Meta на Последнем экзамене человечества в 2026 году, 55% или выше?
26%
Да
Не доверяй внешним ссылкам.
Не доверяй внешним ссылкам.
Часто задаваемые вопросы