Find AI benchmarks with traceable data, licences, and scores. AI Benchmark Index lists benchmarks. Call list_places and list_categories first to learn the place and category slugs. Then call search_listings, and get_listing for one record. Every result has meta.attribution and meta.sources. Show th…
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"ai-benchmark-index","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Not distributed through a package registry we index.
| when | check | result | http | latency | detail |
|---|---|---|---|---|---|
| 6 h ago | mcp initialize | ok | 200 | 804 ms | server aibenchmarkindex 1 · protocol 2025-06-18 · 6 tools |
| 13 h ago | mcp initialize | ok | 200 | 83 ms | server aibenchmarkindex 1 · protocol 2025-06-18 · 6 tools |
| 20 h ago | mcp initialize | ok | 200 | 125 ms | server aibenchmarkindex 1 · protocol 2025-06-18 · 6 tools |
| 27 h ago | mcp initialize | ok | 200 | 204 ms | server aibenchmarkindex 1 · protocol 2025-06-18 · 6 tools |
| 33 h ago | mcp initialize | ok | 200 | 193 ms | server aibenchmarkindex 1 · protocol 2025-06-18 · 6 tools |
| 2 d ago | mcp initialize | ok | 200 | 712 ms | server aibenchmarkindex 1 · protocol 2025-06-18 · 6 tools |
Attributed to the source that supplied each field. Treated as claims, not facts.
Find AI benchmarks with traceable data, licences, and scores. AI Benchmark Index lists benchmarks. Call list_places and list_categories first to learn the place and category slugs. Then call search_listings, and get_listing for one record. Every result has meta.attribution and meta.sources. Show the credit line, and keep the license of each source. A benchmark with indexable false is public data. Its page is kept out of search engines. A benchmark is a record, not an endorsement.
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.