livecodebench/livecodebench

Coding

LiveCodeBench: contamination-free coding benchmark continuously collected from LeetCode, AtCoder, and Codeforces, supporting code generation, self-repair, execution, and test-output prediction.

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/livecodebench --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import livecodebench

eval(livecodebench(), model="openai/gpt-5")

Dataset information

Harbor registry	livecodebench/livecodebench
Inspect task	`livecodebench`
Latest digest	sha256:4dbb3336efa78b7c4d98061d4bdb57af31a2cd52a938b44463e8351ad73b160b
Samples	100
Paper	arxiv
Source	https://github.com/LiveCodeBench/LiveCodeBench

See Task Parameters for the parameter set shared across all Harbor tasks.