yanagiorigami/frontier-cs
Coding
Reasoning
Frontier-CS competitive programming benchmark: 172 open-ended algorithmic problems with partial scoring via go-judge.
Run this task
CLI:
inspect eval inspect_harbor/yanagiorigami_frontier_cs --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import yanagiorigami_frontier_cs
eval(yanagiorigami_frontier_cs(), model="openai/gpt-5")Dataset information
| Harbor registry | yanagiorigami/frontier-cs |
| Inspect task | yanagiorigami_frontier_cs |
| Latest digest | sha256:b48d2701dab90df880efcb1228d9706377cf0f786f06db6734c15b3c9d52a8df |
| Samples | 172 |
| Paper | arxiv |
| Source | https://github.com/FrontierCS/Frontier-CS |
See Task Parameters for the parameter set shared across all Harbor tasks.