quixbugs@1.0
Coding
QuixBugs is a multi-lingual program repair benchmark with 40 Python and 40 Java programs, each containing a single-line defect. Tasks cover algorithms and data structures including sorting, graph, dynamic programming, math, and string/array operations.
Run this task
CLI:
inspect eval inspect_harbor/quixbugs_1_0 --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import quixbugs_1_0
eval(quixbugs_1_0(), model="openai/gpt-5")Dataset information
| Harbor registry | quixbugs@1.0 |
| Inspect task | quixbugs_1_0 |
| Version | 1.0 |
| Samples | 80 |
| Source | https://github.com/jkoppel/QuixBugs |
See Task Parameters for the parameter set shared across all Harbor tasks.