bixbench@1.5

BixBench - A benchmark for evaluating AI agents on bioinformatics and computational biology tasks.

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/bixbench_1_5 --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import bixbench_1_5

eval(bixbench_1_5(), model="openai/gpt-5")

Dataset information

Harbor registry	bixbench@1.5
Inspect task	bixbench_1_5
Version	1.5
Samples	205
Paper	arxiv

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