tinycomputerai/bun-server-bench
Coding
bun-server-bench: a correctness benchmark of 50 production-shaped Bun server engineering tasks for evaluating AI coding agents.
Run this task
CLI:
inspect eval inspect_harbor/tinycomputerai_bun_server_bench --model openai/gpt-5Python:
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.