webgen-bench/webgen-bench
Coding
WebGen-Bench: evaluating LLMs on generating interactive and functional websites from scratch.
Run this task
CLI:
inspect eval inspect_harbor/webgen_bench --model openai/gpt-5Python:
from inspect_ai import eval
from inspect_harbor import webgen_bench
eval(webgen_bench(), model="openai/gpt-5")Dataset information
| Harbor registry | webgen-bench/webgen-bench |
| Inspect task | webgen_bench |
| Latest digest | sha256:e593e93b325f9942ccae818c2a5d4adedbd837ac2aad96c6c3e3fe623be29374 |
| Samples | 101 |
| Paper | arxiv |
| Source | https://github.com/mnluzimu/WebGen-Bench |
See Task Parameters for the parameter set shared across all Harbor tasks.