ml-dev-bench@1.0

ML-Dev-Bench: A benchmark for testing AI agents on machine learning development tasks including model implementation, training, debugging, and optimization.

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/ml_dev_bench_1_0 --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import ml_dev_bench_1_0

eval(ml_dev_bench_1_0(), model="openai/gpt-5")

Dataset information

Harbor registry	ml-dev-bench@1.0
Inspect task	ml_dev_bench_1_0
Version	1.0
Samples	33
Paper	arxiv

See Task Parameters for the parameter set shared across all Harbor tasks.