HyperAIHyperAI

Command Palette

Search for a command to run...

SciCode

A scientist-curated coding benchmark featuring 288 test set subproblems from 80 laboratory problems across 16 scientific disciplines.

Models
142 current, 251 in total
Median
48.7%
Range
6.9%–67.7%

Score distribution

Lowest
6.9%
Median
48.7%
Highest
67.7%

Leaderboard

Data from Artificial Analysis