rounakbende10/rh-swe-bench

Coding

Red Hat SWE-bench - 341 verified tasks from 25 RH ecosystem repos.

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/rounakbende10_rh_swe_bench --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import rounakbende10_rh_swe_bench

eval(rounakbende10_rh_swe_bench(), model="openai/gpt-5")

Dataset information

Harbor registry rounakbende10/rh-swe-bench
Inspect task rounakbende10_rh_swe_bench
Latest digest sha256:96005bdeb80c90e6a487df8cb893dc2856b2bec88d122a14580abcc58481ef75
Samples 341
Source https://github.com/rounakbende10/rh-swe-bench

See Task Parameters for the parameter set shared across all Harbor tasks.