Moonshot AI’s Kimi K3 currently posts 46.9% on Humanity’s Last Exam (HLE), trailing Claude Fable 5 (55.5%) and several other frontier models. Recent Kimi variants, including K2 Thinking and the agentic Kimi-Researcher, demonstrated gains through extended tool-use chains and multi-step reasoning, yet overall scores remain well below the 50% threshold that would close the gap with Anthropic and OpenAI. Trader sentiment hinges on whether Moonshot can release an upgraded model or agent framework before year-end that pushes Kimi past 50% or higher on the 2,500-question expert benchmark. Key catalysts include any new Kimi launch announcements, updated HLE leaderboards, or credible reports of internal scaling and reinforcement-learning improvements at Moonshot through late 2026.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated$18,709 Vol.
Dec 31, 2026
45%+
94%
50%+
61%
55%+
38%
60%+
17%
65%+
5%
$18,709 Vol.
45%+
$3,599 Vol.
94%
50%+
$9,111 Vol.
61%
55%+
$350 Vol.
38%
60%+
$5,194 Vol.
17%
65%+
$454 Vol.
5%
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 Kimi K3 currently posts 46.9% on Humanity’s Last Exam (HLE), trailing Claude Fable 5 (55.5%) and several other frontier models. Recent Kimi variants, including K2 Thinking and the agentic Kimi-Researcher, demonstrated gains through extended tool-use chains and multi-step reasoning, yet overall scores remain well below the 50% threshold that would close the gap with Anthropic and OpenAI. Trader sentiment hinges on whether Moonshot can release an upgraded model or agent framework before year-end that pushes Kimi past 50% or higher on the 2,500-question expert benchmark. Key catalysts include any new Kimi launch announcements, updated HLE leaderboards, or credible reports of internal scaling and reinforcement-learning improvements at Moonshot through late 2026.
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".
Market Opened: Jul 23, 2026, 6:43 PM ET
Volume
$18,709End Date
Dec 31, 2026Market Opened
Jul 23, 2026, 6:43 PM ETResolution Source
https://agi.safe.ai/Resolver
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 Kimi K3 currently posts 46.9% on Humanity’s Last Exam (HLE), trailing Claude Fable 5 (55.5%) and several other frontier models. Recent Kimi variants, including K2 Thinking and the agentic Kimi-Researcher, demonstrated gains through extended tool-use chains and multi-step reasoning, yet overall scores remain well below the 50% threshold that would close the gap with Anthropic and OpenAI. Trader sentiment hinges on whether Moonshot can release an upgraded model or agent framework before year-end that pushes Kimi past 50% or higher on the 2,500-question expert benchmark. Key catalysts include any new Kimi launch announcements, updated HLE leaderboards, or credible reports of internal scaling and reinforcement-learning improvements at Moonshot through late 2026.
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".
Volume
$18,709End Date
Dec 31, 2026Market Opened
Jul 23, 2026, 6:43 PM ETResolution Source
https://agi.safe.ai/Resolver
0x65070BE91...Moonshot AI’s Kimi K3 currently posts 46.9% on Humanity’s Last Exam (HLE), trailing Claude Fable 5 (55.5%) and several other frontier models. Recent Kimi variants, including K2 Thinking and the agentic Kimi-Researcher, demonstrated gains through extended tool-use chains and multi-step reasoning, yet overall scores remain well below the 50% threshold that would close the gap with Anthropic and OpenAI. Trader sentiment hinges on whether Moonshot can release an upgraded model or agent framework before year-end that pushes Kimi past 50% or higher on the 2,500-question expert benchmark. Key catalysts include any new Kimi launch announcements, updated HLE leaderboards, or credible reports of internal scaling and reinforcement-learning improvements at Moonshot through late 2026.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated
Beware of external links.
Beware of external links.
Frequently Asked Questions