bird-bench@parity

Coding

BIRD SQL parity subset (150 tasks, seed 42).

← Back to Registry

Run this task

CLI:

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

Python:

from inspect_ai import eval
from inspect_harbor import bird_bench_parity

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

Dataset information

Harbor registry bird-bench@parity
Inspect task bird_bench_parity
Version parity
Samples 150
Paper arxiv

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