Ranking / Humanity's Sixth Sense

Humanity's Sixth Sense

Data updated 13 Oct 2026

Bucket

Supporting evidence

Unit

percent

Direction

Higher is better

Version

unversioned

Display harness

HSS · max

Board

https://labs.scale.com/leaderboard/hss

Humanity's Sixth Sense by Scale AI + Elorian reports full 522-task pass@1, averaged over three attempts per task. All rubric criteria must pass. The ± value is a 95% task-cluster bootstrap half-width. The unversioned board preserves explicit efforts; unlabelled rows remain unspecified. Capture dates are not evaluation dates. These rows stay out of weighted Overall and capability scores.

Compare published benchmark results with category weights →

Models

Results are ordered by score in the display harness, followed by models with no result. Other harnesses are listed separately below. Missing results remain unknown.

426–450 of 469 entries

Other harnesses

These runs use other harnesses. Capability scoring matches configurations separately; model details identify which source records contribute.