OpenAI models currently trail leaders on Humanity’s Last Exam (HLE), a 2,500-question expert-level benchmark testing graduate knowledge across math, physics, biology, and other domains, with Anthropic’s Claude Opus 5 and Mythos 5 variants holding top scores near 64–65% as of late August 2026. OpenAI’s strongest entries, including GPT-5.4 Pro at 58.7% and GPT-5.6 Sol around 49.5%, reflect gains from iterative GPT-5 releases, enhanced chain-of-thought reasoning, and agentic tool use, though these lag behind Anthropic’s and Meta’s Muse Spark 1.1 (62.1%). Trader sentiment centers on whether upcoming GPT-5.5/5.6 variants or new reasoning architectures can close the gap before year-end resolution, as rapid benchmark progress has outpaced initial 2025 projections but remains far from saturation. Key catalysts include any confirmed OpenAI model launches or capability demos through December.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated$52,239 Vol.
Dec 31, 2026
50%+
88%
55%+
57%
60%+
30%
65%+
9%
70%+
7%
$52,239 Vol.
50%+
$9,227 Vol.
88%
55%+
$19,880 Vol.
57%
60%+
$17,543 Vol.
30%
65%+
$3,050 Vol.
9%
70%+
$2,540 Vol.
7%
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 models currently trail leaders on Humanity’s Last Exam (HLE), a 2,500-question expert-level benchmark testing graduate knowledge across math, physics, biology, and other domains, with Anthropic’s Claude Opus 5 and Mythos 5 variants holding top scores near 64–65% as of late August 2026. OpenAI’s strongest entries, including GPT-5.4 Pro at 58.7% and GPT-5.6 Sol around 49.5%, reflect gains from iterative GPT-5 releases, enhanced chain-of-thought reasoning, and agentic tool use, though these lag behind Anthropic’s and Meta’s Muse Spark 1.1 (62.1%). Trader sentiment centers on whether upcoming GPT-5.5/5.6 variants or new reasoning architectures can close the gap before year-end resolution, as rapid benchmark progress has outpaced initial 2025 projections but remains far from saturation. Key catalysts include any confirmed OpenAI model launches or capability demos through December.
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".
Market Opened: Jul 23, 2026, 6:53 PM ET
Volume
$52,239End Date
Jan 1, 2027Market Opened
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 models currently trail leaders on Humanity’s Last Exam (HLE), a 2,500-question expert-level benchmark testing graduate knowledge across math, physics, biology, and other domains, with Anthropic’s Claude Opus 5 and Mythos 5 variants holding top scores near 64–65% as of late August 2026. OpenAI’s strongest entries, including GPT-5.4 Pro at 58.7% and GPT-5.6 Sol around 49.5%, reflect gains from iterative GPT-5 releases, enhanced chain-of-thought reasoning, and agentic tool use, though these lag behind Anthropic’s and Meta’s Muse Spark 1.1 (62.1%). Trader sentiment centers on whether upcoming GPT-5.5/5.6 variants or new reasoning architectures can close the gap before year-end resolution, as rapid benchmark progress has outpaced initial 2025 projections but remains far from saturation. Key catalysts include any confirmed OpenAI model launches or capability demos through December.
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".
Volume
$52,239End Date
Jan 1, 2027Market Opened
Jul 23, 2026, 6:53 PM ETResolver
0x65070BE91...OpenAI models currently trail leaders on Humanity’s Last Exam (HLE), a 2,500-question expert-level benchmark testing graduate knowledge across math, physics, biology, and other domains, with Anthropic’s Claude Opus 5 and Mythos 5 variants holding top scores near 64–65% as of late August 2026. OpenAI’s strongest entries, including GPT-5.4 Pro at 58.7% and GPT-5.6 Sol around 49.5%, reflect gains from iterative GPT-5 releases, enhanced chain-of-thought reasoning, and agentic tool use, though these lag behind Anthropic’s and Meta’s Muse Spark 1.1 (62.1%). Trader sentiment centers on whether upcoming GPT-5.5/5.6 variants or new reasoning architectures can close the gap before year-end resolution, as rapid benchmark progress has outpaced initial 2025 projections but remains far from saturation. Key catalysts include any confirmed OpenAI model launches or capability demos through December.
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