blobfishai/counselbench-100

100 high-level legal-agent tasks with 97-asset multi-provider evidence rooms, distinct deep trajectories, and native causal state verification.

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/blobfishai_counselbench_100 --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import blobfishai_counselbench_100

eval(blobfishai_counselbench_100(), model="openai/gpt-5")

Dataset information

Harbor registry	blobfishai/counselbench-100
Inspect task	blobfishai_counselbench_100
Latest digest	sha256:0e2b7e78bbde84c1691ad016f7b2344e5570b98b5545a33ef783a0687e60b6e8
Samples	100

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