maxbittker/runebench

Reasoning
Behavior

Benchmark suite for evaluating AI agents on RuneScape gameplay tasks.

← Back to Registry

Run this task

CLI:

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

Python:

from inspect_ai import eval
from inspect_harbor import maxbittker_runebench

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

Dataset information

Harbor registry maxbittker/runebench
Inspect task maxbittker_runebench
Latest digest sha256:4bb3430af2ef3a320bd3dfeeab2447fbf9e0093452ad747997186a85a060de28
Samples 32
Source https://github.com/MaxBittker/rs-sdk

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