livecodebench@6.0
Coding
A subset of 100 sampled tasks from the release_v6 version of LiveCodeBench tasks.
Run this task
CLI:
inspect eval inspect_harbor/livecodebench_6_0 --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import livecodebench_6_0
eval(livecodebench_6_0(), model="openai/gpt-5")Dataset information
| Harbor registry | livecodebench@6.0 |
| Inspect task | livecodebench_6_0 |
| Version | 6.0 |
| Samples | 100 |
| Paper | arxiv |
See Task Parameters for the parameter set shared across all Harbor tasks.