Anthropic’s Claude Fable 5.1 and Opus 5 currently lead Humanity’s Last Exam (HLE) at 65% and 64.7%, respectively, on the 2,500-question expert-level benchmark covering math, sciences, and humanities. These gains stem from scaled reasoning training, adaptive tool use, and larger context windows that outperform earlier 2025 frontier models stuck below 20%. Meta’s Muse Spark 1.1 sits near 62%, while OpenAI and Google entries trail in the mid-to-high 50s, reflecting differences in post-training and agentic scaffolding. With three months left in 2026, new releases, verified no-tools evaluations, and multimodal extensions could lift the frontier further, though self-reported results and benchmark revisions introduce uncertainty around final resolution.
Résumé expérimental généré par IA à partir des données Polymarket. Ceci n'est pas un conseil de trading et ne joue aucun rôle dans la résolution de ce marché. · Mis à jour$53,627 Vol.
60% ou plus
61%
65 %+
31%
70 %+
17%
75 %+
12%
80 %+
7%
90 %+
4%
$53,627 Vol.
60% ou plus
61%
65 %+
31%
70 %+
17%
75 %+
12%
80 %+
7%
90 %+
4%
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".
Marché ouvert : Jul 23, 2026, 6:41 PM ET
Source de résolution
https://agi.safe.ai/Résolveur
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".
Source de résolution
https://agi.safe.ai/Résolveur
0x65070BE91...Anthropic’s Claude Fable 5.1 and Opus 5 currently lead Humanity’s Last Exam (HLE) at 65% and 64.7%, respectively, on the 2,500-question expert-level benchmark covering math, sciences, and humanities. These gains stem from scaled reasoning training, adaptive tool use, and larger context windows that outperform earlier 2025 frontier models stuck below 20%. Meta’s Muse Spark 1.1 sits near 62%, while OpenAI and Google entries trail in the mid-to-high 50s, reflecting differences in post-training and agentic scaffolding. With three months left in 2026, new releases, verified no-tools evaluations, and multimodal extensions could lift the frontier further, though self-reported results and benchmark revisions introduce uncertainty around final resolution.
Résumé expérimental généré par IA à partir des données Polymarket. Ceci n'est pas un conseil de trading et ne joue aucun rôle dans la résolution de ce marché. · Mis à jour



Méfiez-vous des liens externes.
Méfiez-vous des liens externes.
Questions fréquentes