evoeval@1.0
Coding
EvoEval_difficult: 100 challenging Python programming tasks evolved from HumanEval.
Run this task
CLI:
inspect eval inspect_harbor/evoeval_1_0 --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import evoeval_1_0
eval(evoeval_1_0(), model="openai/gpt-5")Dataset information
| Harbor registry | evoeval@1.0 |
| Inspect task | evoeval_1_0 |
| Version | 1.0 |
| Samples | 100 |
| Source | https://github.com/evo-eval/evoeval |
See Task Parameters for the parameter set shared across all Harbor tasks.