mercor/apex-agents-1-1

Long-horizon professional-services benchmark in investment banking, law, and management consulting, written by practicing analysts, consultants, and corporate lawyers. For evaluation only.

← Back to Registry

Run this task

CLI:

inspect eval inspect_harbor/mercor_apex_agents_1_1 --model openai/gpt-5

Python:

from inspect_ai import eval
from inspect_harbor import mercor_apex_agents_1_1

eval(mercor_apex_agents_1_1(), model="openai/gpt-5")

Dataset information

Harbor registry	mercor/apex-agents-1-1
Inspect task	mercor_apex_agents_1_1
Latest digest	sha256:45f97008d55c5b1f55ad6aff346b1e0308dd1d89265b3a82d3d1f1f66197ff12
Samples	240
Paper	arxiv
Source	https://github.com/Mercor-Intelligence/apex_loop_truncated_tools_agent

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