scale-ai/swe-atlas-qna
Coding
SWE-Atlas - Codebase QnA is a benchmark of deep codebase comprehension and QnA problems for coding agents. Checkout for instructions on running it.
Run this task
CLI:
inspect eval inspect_harbor/scale_ai_swe_atlas_qna --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import scale_ai_swe_atlas_qna
eval(scale_ai_swe_atlas_qna(), model="openai/gpt-5")Dataset information
| Harbor registry | scale-ai/swe-atlas-qna |
| Inspect task | scale_ai_swe_atlas_qna |
| Latest digest | sha256:0e26bc0313ae2fc6f912b67b928e648c7f20d17d91f765f702a93042ce5be0e4 |
| Samples | 124 |
| Source | https://github.com/scaleapi/SWE-Atlas |
See Task Parameters for the parameter set shared across all Harbor tasks.