gabeorlanski/slopcodebench
Coding
SlopCodeBench multi-checkpoint coding benchmark tasks converted for Harbor.
Run this task
CLI:
inspect eval inspect_harbor/gabeorlanski_slopcodebench --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import gabeorlanski_slopcodebench
eval(gabeorlanski_slopcodebench(), model="openai/gpt-5")Dataset information
| Harbor registry | gabeorlanski/slopcodebench |
| Inspect task | gabeorlanski_slopcodebench |
| Latest digest | sha256:73a17cda817d37ce3352d18c272c40a3f6b623061023bee365b4df74adcd11b5 |
| Samples | 36 |
| Paper | arxiv |
| Source | https://github.com/SprocketLab/slop-code-bench |
See Task Parameters for the parameter set shared across all Harbor tasks.