Meta’s Muse Spark 1.1 series has narrowed the gap on Humanity’s Last Exam (HLE), a 2,500-question expert-sourced benchmark spanning math, physics, and other domains that remains unsaturated for frontier large language models. Recent evaluations place Muse Spark variants at 50–62% depending on the leaderboard and reasoning mode, trailing Anthropic’s leading Claude Fable 5 and Opus 5 entries (55–65%) while outperforming several GPT-5 and Gemini previews. Gains stem from expanded training clusters, adaptive reasoning techniques, and post-training refinements. With four months left before the December 31, 2026 resolution, further Meta releases, benchmark revisions, or disclosed scaling advances could lift the company’s peak 2026 result and shift trader consensus on the 55%+, 60%+, and higher thresholds.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated$53,620 Vol.
Dec 31, 2026
55%+
35%
60%+
23%
65%+
18%
70%+
7%
$53,620 Vol.
55%+
$32,344 Vol.
35%
60%+
$11,986 Vol.
23%
65%+
$7,507 Vol.
18%
70%+
$1,783 Vol.
7%
This market will resolve to "Yes" if any model published by Meta 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".Meta’s Muse Spark 1.1 series has narrowed the gap on Humanity’s Last Exam (HLE), a 2,500-question expert-sourced benchmark spanning math, physics, and other domains that remains unsaturated for frontier large language models. Recent evaluations place Muse Spark variants at 50–62% depending on the leaderboard and reasoning mode, trailing Anthropic’s leading Claude Fable 5 and Opus 5 entries (55–65%) while outperforming several GPT-5 and Gemini previews. Gains stem from expanded training clusters, adaptive reasoning techniques, and post-training refinements. With four months left before the December 31, 2026 resolution, further Meta releases, benchmark revisions, or disclosed scaling advances could lift the company’s peak 2026 result and shift trader consensus on the 55%+, 60%+, and higher thresholds.
This market will resolve to "Yes" if any model published by Meta 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, 6:48 PM ET
Volume
$53,620End Date
Jan 1, 2027Market Opened
Jul 23, 2026, 6:48 PM ETResolution Source
https://agi.safe.ai/Resolver
0x65070BE91...This market will resolve to "Yes" if any model published by Meta 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".Meta’s Muse Spark 1.1 series has narrowed the gap on Humanity’s Last Exam (HLE), a 2,500-question expert-sourced benchmark spanning math, physics, and other domains that remains unsaturated for frontier large language models. Recent evaluations place Muse Spark variants at 50–62% depending on the leaderboard and reasoning mode, trailing Anthropic’s leading Claude Fable 5 and Opus 5 entries (55–65%) while outperforming several GPT-5 and Gemini previews. Gains stem from expanded training clusters, adaptive reasoning techniques, and post-training refinements. With four months left before the December 31, 2026 resolution, further Meta releases, benchmark revisions, or disclosed scaling advances could lift the company’s peak 2026 result and shift trader consensus on the 55%+, 60%+, and higher thresholds.
This market will resolve to "Yes" if any model published by Meta 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
$53,620End Date
Jan 1, 2027Market Opened
Jul 23, 2026, 6:48 PM ETResolution Source
https://agi.safe.ai/Resolver
0x65070BE91...Meta’s Muse Spark 1.1 series has narrowed the gap on Humanity’s Last Exam (HLE), a 2,500-question expert-sourced benchmark spanning math, physics, and other domains that remains unsaturated for frontier large language models. Recent evaluations place Muse Spark variants at 50–62% depending on the leaderboard and reasoning mode, trailing Anthropic’s leading Claude Fable 5 and Opus 5 entries (55–65%) while outperforming several GPT-5 and Gemini previews. Gains stem from expanded training clusters, adaptive reasoning techniques, and post-training refinements. With four months left before the December 31, 2026 resolution, further Meta releases, benchmark revisions, or disclosed scaling advances could lift the company’s peak 2026 result and shift trader consensus on the 55%+, 60%+, and higher thresholds.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · UpdatedRelated
Will the highest score achieved on Humanity’s Last Exam in 2026 be 60% or higher?
55%
Will the highest score achieved by an OpenAI model on Humanity’s Last Exam in 2026 be 55% or higher?
82%
Will the highest score achieved by an Anthropic Claude model on Humanity’s Last Exam in 2026 be 55% or higher?
84%
Beware of external links.
Beware of external links.
Frequently Asked Questions