crustbench/crustbench
Coding
CRUST-Bench: real-world C repositories paired with hand-written safe-Rust interfaces and tests, benchmarking LLMs on C-to-safe-Rust transpilation.
Run this task
CLI:
inspect eval inspect_harbor/crustbench --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import crustbench
eval(crustbench(), model="openai/gpt-5")Dataset information
| Harbor registry | crustbench/crustbench |
| Inspect task | crustbench |
| Latest digest | sha256:a474b77ebbe183daf14e367e1b9d6e7aa148634a982bfb0e937944743f618243 |
| Samples | 100 |
| Paper | arxiv |
| Source | https://github.com/anirudhkhatry/CRUST-bench |
See Task Parameters for the parameter set shared across all Harbor tasks.