Google's Gemini series trails Anthropic's Claude models on Humanity’s Last Exam (HLE), a 2,500-question expert-level benchmark spanning mathematics, physics, biology, and humanities, with recent no-tools scores showing Gemini 3.1 Pro near 45% versus Claude Fable 5.1 at 61%. Trader focus centers on Google's accelerated 2026 release cadence, including mid-August Gemini 3.7 Flash and ongoing 3.8 variant testing, alongside pre-training for Gemini 4 expected later this year. These updates target improved multi-step reasoning and reduced errors on frontier questions that reward depth over retrieval. The benchmark remains far from saturation, with top scores in the low-to-mid 60s percent range, leaving room for late-year Gemini gains before the December 31 resolution.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated$90,044 Vol.
Dec 31, 2026
50%+
91%
55%+
36%
60%+
21%
65%+
12%
70%+
4%
$90,044 Vol.
50%+
$30,496 Vol.
91%
55%+
$34,274 Vol.
36%
60%+
$15,671 Vol.
21%
65%+
$5,246 Vol.
12%
70%+
$4,358 Vol.
4%
This market will resolve to "Yes" if any Google Gemini 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".Google's Gemini series trails Anthropic's Claude models on Humanity’s Last Exam (HLE), a 2,500-question expert-level benchmark spanning mathematics, physics, biology, and humanities, with recent no-tools scores showing Gemini 3.1 Pro near 45% versus Claude Fable 5.1 at 61%. Trader focus centers on Google's accelerated 2026 release cadence, including mid-August Gemini 3.7 Flash and ongoing 3.8 variant testing, alongside pre-training for Gemini 4 expected later this year. These updates target improved multi-step reasoning and reduced errors on frontier questions that reward depth over retrieval. The benchmark remains far from saturation, with top scores in the low-to-mid 60s percent range, leaving room for late-year Gemini gains before the December 31 resolution.
This market will resolve to "Yes" if any Google Gemini 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, 6:56 PM ET
Volume
$90,044End Date
Jan 1, 2027Market Opened
Jul 23, 2026, 6:56 PM ETResolver
0x65070BE91...This market will resolve to "Yes" if any Google Gemini 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".Google's Gemini series trails Anthropic's Claude models on Humanity’s Last Exam (HLE), a 2,500-question expert-level benchmark spanning mathematics, physics, biology, and humanities, with recent no-tools scores showing Gemini 3.1 Pro near 45% versus Claude Fable 5.1 at 61%. Trader focus centers on Google's accelerated 2026 release cadence, including mid-August Gemini 3.7 Flash and ongoing 3.8 variant testing, alongside pre-training for Gemini 4 expected later this year. These updates target improved multi-step reasoning and reduced errors on frontier questions that reward depth over retrieval. The benchmark remains far from saturation, with top scores in the low-to-mid 60s percent range, leaving room for late-year Gemini gains before the December 31 resolution.
This market will resolve to "Yes" if any Google Gemini 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
$90,044End Date
Jan 1, 2027Market Opened
Jul 23, 2026, 6:56 PM ETResolver
0x65070BE91...Google's Gemini series trails Anthropic's Claude models on Humanity’s Last Exam (HLE), a 2,500-question expert-level benchmark spanning mathematics, physics, biology, and humanities, with recent no-tools scores showing Gemini 3.1 Pro near 45% versus Claude Fable 5.1 at 61%. Trader focus centers on Google's accelerated 2026 release cadence, including mid-August Gemini 3.7 Flash and ongoing 3.8 variant testing, alongside pre-training for Gemini 4 expected later this year. These updates target improved multi-step reasoning and reduced errors on frontier questions that reward depth over retrieval. The benchmark remains far from saturation, with top scores in the low-to-mid 60s percent range, leaving room for late-year Gemini gains before the December 31 resolution.
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