Skip to main content AI Studio  add-on for Spider.

Measure everything. Publish the method.

Spider Research is the lab layer of Spider: open benchmarks and field notes on web data quality for AI. Every number links to a method; every method links to a repo.

spider-rs/benchmark ↗

The record.

Each entry is a dated snapshot of a maintained measurement. Where a repo exists, the numbers reproduce from a clone.

Stealth Bench V1.

Completeness under anti-bot pressure — the same tasks, the same judge, every provider. Clone the repo and rerun it.

Stealth Bench V1: Spider leads with 84.5% success rate across 71 anti-bot tasks.Spider84.5%Browser Use81.4%Anchor76.8%Onkernel67.1%Browserless54%Steel47.2%Browserbase41.9%Hyperbrowser39.9%

Method · spider-rs/benchmark ↗

Next · Quality Bench v1 — extraction fidelity, HTML → ground-truth markdown · 1,000-URL dataset drop · Silk structure-conformance eval

Judge the output yourself.

Post a URL, read what comes back. A failed request bills $0.