crustbench@1.0
Coding
CRUST-bench: 100 C-to-safe-Rust transpilation tasks from real-world C repositories.
Run this task
CLI:
inspect eval inspect_harbor/crustbench_1_0 --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import crustbench_1_0
eval(crustbench_1_0(), model="openai/gpt-5")Dataset information
| Harbor registry | crustbench@1.0 |
| Inspect task | crustbench_1_0 |
| Version | 1.0 |
| Samples | 100 |
| Paper | arxiv |
See Task Parameters for the parameter set shared across all Harbor tasks.