**Anthropic’s recent Claude Fable 5.1 and Mythos 5.1 releases (early September 2026) have driven current trader sentiment, pushing the models to the top of HLE leaderboards with reported scores of 59–65% depending on configuration (tools, reasoning effort, or adaptive settings).** These iterative advances in reasoning, tool use, and long-context handling have kept multiple Claude variants (Fable 5.1, Opus 5, Mythos 5) clustered at the frontier ahead of OpenAI’s GPT-6 Astra (~54–57%) and models from Google, Meta, and others. HLE’s expert-sourced 2,500-question design across math, sciences, and humanities has seen rapid progress in 2026, with the benchmark still far from saturation. Key upcoming catalysts include any late-2026 Anthropic updates or competitor breakthroughs before the December 31 resolution; self-reported results and varying verification add uncertainty around exact thresholds like 60%+.
Experimental AI-generated summary referencing Polymarket data. This is not trading advice and plays no role in how this market resolves. · Updated$88,043 Vol.
Dec 31, 2026
55%+
90%
60%+
57%
65%+
26%
70%+
7%
75%+
6%
$88,043 Vol.
55%+
$18,754 Vol.
90%
60%+
$37,881 Vol.
57%
65%+
$26,265 Vol.
26%
70%+
$3,859 Vol.
7%
75%+
$1,284 Vol.
6%
This market will resolve to "Yes" if any Anthropic Claude 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".**Anthropic’s recent Claude Fable 5.1 and Mythos 5.1 releases (early September 2026) have driven current trader sentiment, pushing the models to the top of HLE leaderboards with reported scores of 59–65% depending on configuration (tools, reasoning effort, or adaptive settings).** These iterative advances in reasoning, tool use, and long-context handling have kept multiple Claude variants (Fable 5.1, Opus 5, Mythos 5) clustered at the frontier ahead of OpenAI’s GPT-6 Astra (~54–57%) and models from Google, Meta, and others. HLE’s expert-sourced 2,500-question design across math, sciences, and humanities has seen rapid progress in 2026, with the benchmark still far from saturation. Key upcoming catalysts include any late-2026 Anthropic updates or competitor breakthroughs before the December 31 resolution; self-reported results and varying verification add uncertainty around exact thresholds like 60%+.
This market will resolve to "Yes" if any Anthropic Claude 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, 6:42 PM ET
Volume
$88,043End Date
Jan 1, 2027Market Opened
Jul 23, 2026, 6:42 PM ETResolution Source
https://agi.safe.ai/Resolver
0x65070BE91...This market will resolve to "Yes" if any Anthropic Claude 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".**Anthropic’s recent Claude Fable 5.1 and Mythos 5.1 releases (early September 2026) have driven current trader sentiment, pushing the models to the top of HLE leaderboards with reported scores of 59–65% depending on configuration (tools, reasoning effort, or adaptive settings).** These iterative advances in reasoning, tool use, and long-context handling have kept multiple Claude variants (Fable 5.1, Opus 5, Mythos 5) clustered at the frontier ahead of OpenAI’s GPT-6 Astra (~54–57%) and models from Google, Meta, and others. HLE’s expert-sourced 2,500-question design across math, sciences, and humanities has seen rapid progress in 2026, with the benchmark still far from saturation. Key upcoming catalysts include any late-2026 Anthropic updates or competitor breakthroughs before the December 31 resolution; self-reported results and varying verification add uncertainty around exact thresholds like 60%+.
This market will resolve to "Yes" if any Anthropic Claude 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
$88,043End Date
Jan 1, 2027Market Opened
Jul 23, 2026, 6:42 PM ETResolution Source
https://agi.safe.ai/Resolver
0x65070BE91...**Anthropic’s recent Claude Fable 5.1 and Mythos 5.1 releases (early September 2026) have driven current trader sentiment, pushing the models to the top of HLE leaderboards with reported scores of 59–65% depending on configuration (tools, reasoning effort, or adaptive settings).** These iterative advances in reasoning, tool use, and long-context handling have kept multiple Claude variants (Fable 5.1, Opus 5, Mythos 5) clustered at the frontier ahead of OpenAI’s GPT-6 Astra (~54–57%) and models from Google, Meta, and others. HLE’s expert-sourced 2,500-question design across math, sciences, and humanities has seen rapid progress in 2026, with the benchmark still far from saturation. Key upcoming catalysts include any late-2026 Anthropic updates or competitor breakthroughs before the December 31 resolution; self-reported results and varying verification add uncertainty around exact thresholds like 60%+.
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