Meta’s Muse Spark 1.1 model has driven recent trader sentiment by posting scores near 62% on HLE leaderboards as of early September 2026, placing it close behind Anthropic’s leading Claude Fable 5.1 at 65% while ahead of several OpenAI GPT-5 variants. This benchmark’s 2,500 expert-level questions across math, sciences, and humanities remain far from saturated, rewarding advances in reasoning chains, tool use, and post-training refinements. Meta’s competitive positioning benefits from rapid iteration on its frontier models and open-weight ecosystem, though outcomes hinge on whether further 2026 releases can close the gap to or exceed 65% before year-end amid ongoing Anthropic and Google DeepMind progress.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated$39,525 Vol.
55%+
44%
60%+
26%
65%+
13%
70%+
8%
$39,525 Vol.
55%+
44%
60%+
26%
65%+
13%
70%+
8%
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
Resolution Source
https://agi.safe.ai/Resolver
0x65070BE91...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".
Resolution Source
https://agi.safe.ai/Resolver
0x65070BE91...Meta’s Muse Spark 1.1 model has driven recent trader sentiment by posting scores near 62% on HLE leaderboards as of early September 2026, placing it close behind Anthropic’s leading Claude Fable 5.1 at 65% while ahead of several OpenAI GPT-5 variants. This benchmark’s 2,500 expert-level questions across math, sciences, and humanities remain far from saturated, rewarding advances in reasoning chains, tool use, and post-training refinements. Meta’s competitive positioning benefits from rapid iteration on its frontier models and open-weight ecosystem, though outcomes hinge on whether further 2026 releases can close the gap to or exceed 65% before year-end amid ongoing Anthropic and Google DeepMind progress.
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