HyperAIHyperAI

Command Palette

Search for a command to run...

LiveCodeBench

A contamination-free coding benchmark that continuously harvests fresh competitive programming problems from LeetCode, AtCoder, and CodeForces, evaluating code generation, self-repair, and execution.

Models
82 current, 343 in total
Median
47.2%
Range
0.3%–87.8%

Score distribution

Lowest
0.3%
Median
47.2%
Highest
87.8%

Leaderboard

Data from Artificial Analysis