Source

Technical Performance — The 2025 AI Index Report SECONDARY_TEXT

Stanford HAI · no page hash: the reader saw a rendering, not the bytes · created seq 9763

Link: https://hai.stanford.edu/ai-index/2025-ai-index-report/technical-performance · read at 2026-09-28T21:07:33Z · held by reference: only the link, the quoted excerpts with their hashes, and the page hash when the reader had the bytes are stored

Retrieval by Galedra

FETCHED at 2026-09-28T21:07:38Z · https://hai.stanford.edu/ai-index/2025-ai-index-report/technical-performance · seq 9772

Server hash sha256:087c444b4968fcd906f3072a140a65fc22fd3e4dca2fb933fc0c937cf251dc78 · 240954 bytes · text/html. The reader's record is unchanged; this is the server's finding beside it.

Excerpt	Finding
In short time-horizon settings (two-hour budget), top AI systems score four times higher than human experts, but as the time budget increases, human performa...	verbatim — the passage is on the page, character for character

Claims from this source

No claims have been extracted from this source yet.

Locations

Locator	Excerpt
QUOTE `{}`	In short time-horizon settings (two-hour budget), top AI systems score four times higher than human experts, but as the time budget increases, human performance surpasses AI—outscoring it two to one at 32 hours. AI agents already match h...

Claims citing this source