swesmith@1.0
Coding
SWE-smith is a synthetically generated dataset of software engineering tasks derived from GitHub issues for training and evaluating code generation models.
Run this task
CLI:
inspect eval inspect_harbor/swesmith_1_0 --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import swesmith_1_0
eval(swesmith_1_0(), model="openai/gpt-5")Dataset information
| Harbor registry | swesmith@1.0 |
| Inspect task | swesmith_1_0 |
| Version | 1.0 |
| Samples | 100 |
| Paper | arxiv |
See Task Parameters for the parameter set shared across all Harbor tasks.