blobfishai/semikongbench-100
100 executable semiconductor exception workflows with deterministic SemiOpsScore grading.
Run this task
CLI:
inspect eval inspect_harbor/blobfishai_semikongbench_100 --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import blobfishai_semikongbench_100
eval(blobfishai_semikongbench_100(), model="openai/gpt-5")Dataset information
| Harbor registry | blobfishai/semikongbench-100 |
| Inspect task | blobfishai_semikongbench_100 |
| Latest digest | sha256:98ce5f040e311b2555d4eb7d3b4779a69f5ec5ea5d0a9aeae80b487588f2d6ff |
| Samples | 100 |
See Task Parameters for the parameter set shared across all Harbor tasks.