tinycomputerai/bun-server-bench

Coding

bun-server-bench: a correctness benchmark of 50 production-shaped Bun server engineering tasks for evaluating AI coding agents.

← Back to Registry

Run this task

CLI:

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

Python:

from inspect_ai import eval
from inspect_harbor import tinycomputerai_bun_server_bench

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

Dataset information

Harbor registry tinycomputerai/bun-server-bench
Inspect task tinycomputerai_bun_server_bench
Latest digest sha256:fa582e2f208b5e8855f71b3f51d5cca140643e52e1b5aaedb37b6f003618f4ae
Samples 50
Source https://github.com/tinycomputerai/bun-server-bench

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