Recent Gemini releases, including 3.1 Pro and 3 Deep Think variants, have lifted Google’s scores on Humanity’s Last Exam (HLE) into the low-to-mid 40s percent range on text-only evaluations as of mid-2026, yet these trail Anthropic’s Claude Opus 5 and Mythos 5 (55-65% on verified leaderboards) and several OpenAI GPT-5 configurations. HLE’s 2,500 expert-authored questions across math, physics, biology, and humanities continue to expose gaps in long-chain reasoning and calibration even as overall frontier performance rises rapidly from single digits in early 2025. Google’s DeepMind team emphasizes multimodal and tool-augmented testing, while competitors prioritize specialized reasoning modes; any new Gemini 3.x update or post-training run before year-end could narrow the gap. Traders watch release cadence, benchmark-specific ablations, and whether Google closes the roughly 10-15 point deficit before December 31.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated$47,300 Vol.
Dec 31, 2026
50%+
72%
55%+
42%
60%+
26%
65%+
14%
70%+
6%
$47,300 Vol.
50%+
$20,691 Vol.
72%
55%+
$7,723 Vol.
42%
60%+
$9,550 Vol.
26%
65%+
$4,988 Vol.
14%
70%+
$4,348 Vol.
6%
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".Recent Gemini releases, including 3.1 Pro and 3 Deep Think variants, have lifted Google’s scores on Humanity’s Last Exam (HLE) into the low-to-mid 40s percent range on text-only evaluations as of mid-2026, yet these trail Anthropic’s Claude Opus 5 and Mythos 5 (55-65% on verified leaderboards) and several OpenAI GPT-5 configurations. HLE’s 2,500 expert-authored questions across math, physics, biology, and humanities continue to expose gaps in long-chain reasoning and calibration even as overall frontier performance rises rapidly from single digits in early 2025. Google’s DeepMind team emphasizes multimodal and tool-augmented testing, while competitors prioritize specialized reasoning modes; any new Gemini 3.x update or post-training run before year-end could narrow the gap. Traders watch release cadence, benchmark-specific ablations, and whether Google closes the roughly 10-15 point deficit before December 31.
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
$47,300End Date
Dec 31, 2026Market 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".Recent Gemini releases, including 3.1 Pro and 3 Deep Think variants, have lifted Google’s scores on Humanity’s Last Exam (HLE) into the low-to-mid 40s percent range on text-only evaluations as of mid-2026, yet these trail Anthropic’s Claude Opus 5 and Mythos 5 (55-65% on verified leaderboards) and several OpenAI GPT-5 configurations. HLE’s 2,500 expert-authored questions across math, physics, biology, and humanities continue to expose gaps in long-chain reasoning and calibration even as overall frontier performance rises rapidly from single digits in early 2025. Google’s DeepMind team emphasizes multimodal and tool-augmented testing, while competitors prioritize specialized reasoning modes; any new Gemini 3.x update or post-training run before year-end could narrow the gap. Traders watch release cadence, benchmark-specific ablations, and whether Google closes the roughly 10-15 point deficit before December 31.
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
$47,300End Date
Dec 31, 2026Market Opened
Jul 23, 2026, 6:56 PM ETResolver
0x65070BE91...Recent Gemini releases, including 3.1 Pro and 3 Deep Think variants, have lifted Google’s scores on Humanity’s Last Exam (HLE) into the low-to-mid 40s percent range on text-only evaluations as of mid-2026, yet these trail Anthropic’s Claude Opus 5 and Mythos 5 (55-65% on verified leaderboards) and several OpenAI GPT-5 configurations. HLE’s 2,500 expert-authored questions across math, physics, biology, and humanities continue to expose gaps in long-chain reasoning and calibration even as overall frontier performance rises rapidly from single digits in early 2025. Google’s DeepMind team emphasizes multimodal and tool-augmented testing, while competitors prioritize specialized reasoning modes; any new Gemini 3.x update or post-training run before year-end could narrow the gap. Traders watch release cadence, benchmark-specific ablations, and whether Google closes the roughly 10-15 point deficit before December 31.
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