Yes65%
No35%
Sep 2Sep 9Sep 16Sep 24Oct 2
100%75%50%25%0%

The deciding value is the highest average score of any AI agent on the GAIA (General AI Assistants) Leaderboard published by the GAIA Benchmark on Hugging Face Spaces, taken from the column for overall average performance (currently labeled Average score (%)) at 1:00 PM CT on December 31, 2026. Values are read at the precision displayed on the leaderboard, only entries visible on the public leaderboard at that time count regardless of later removal or changes, and if the leaderboard is temporarily unavailable, the first value published after that time is used. The outcome is Yes if that highest score is at least the value specified in the market question and No otherwise. The outcome is not determined early and becomes final at 1:00 PM CT on that date.
AI agents are systems that carry out multi-step tasks on a user's behalf, such as searching the web, using tools, and reasoning over files. The measure is the highest overall average score achieved by any AI agent on the General AI Assistants (GAIA) benchmark on December 31, 2026.

The deciding value is the highest average score of any AI agent on the GAIA (General AI Assistants) Leaderboard published by the GAIA Benchmark on Hugging Face Spaces, taken from the column for overall average performance (currently labeled Average score (%)) at 1:00 PM CT on December 31, 2026. Values are read at the precision displayed on the leaderboard, only entries visible on the public leaderboard at that time count regardless of later removal or changes, and if the leaderboard is temporarily unavailable, the first value published after that time is used. The outcome is Yes if that highest score is at least the value specified in the market question and No otherwise. The outcome is not determined early and becomes final at 1:00 PM CT on that date.
AI agents are systems that carry out multi-step tasks on a user's behalf, such as searching the web, using tools, and reasoning over files. The measure is the highest overall average score achieved by any AI agent on the General AI Assistants (GAIA) benchmark on December 31, 2026.