featurebench/featurebench-lite-modal
Coding
FeatureBench-Lite executed on Modal’s cloud sandbox runner.
Run this task
CLI:
inspect eval inspect_harbor/featurebench_lite_modal --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import featurebench_lite_modal
eval(featurebench_lite_modal(), model="openai/gpt-5")Dataset information
| Harbor registry | featurebench/featurebench-lite-modal |
| Inspect task | featurebench_lite_modal |
| Latest digest | sha256:093962d407d0bca2bfc593721e4cd58c09159aa58403a7988835a2b7aeee0f4c |
| Samples | 30 |
| Paper | arxiv |
See Task Parameters for the parameter set shared across all Harbor tasks.