Leaderboard / agent-data.centorprat.workers.dev / endpoint
GET https://agent-data.centorprat.workers.dev/web/research
Scores measure reliability and honesty, not output quality.
- Listed only 1 day ago; new listings earn trust over 30 days.
- Answered all 7 probes in the last 7 days.
- Category
- Web search by llm, confidence 80%
- Latest quote
- $0.05 on Base to 0x8d38…B120
- Uptime
- 100% / 7d, 100% / 30d
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 17m ago
- Next probe
- 2026-11-17 23:13 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Polygon | 0x3c49…3359 | 50000 | 0x8d38…B120 | default | yes | 4h ago |
| cdp | exact | Base | 0x8335…2913 | $0.05 | 0x8d38…B120 | default | yes | 4h ago |
| cdp | exact | Solana | EPjFWd…Dt1v | 50000 | 3644Dr…RHQh | default | yes | 4h ago |
Paid probes
No paid probes yet. Paid probing is off by default and runs weekly per host under a strict spend cap; each paid probe links to its on-chain transaction here.
Delivery checks
Inside each paid probe we ask for something whose correct answer we know, then compare. A pass means the seller delivered what it was paid for; a fail means it charged and returned something wrong; inconclusive means we could not judge (no reference, unknown input shape, or a non-2xx response). Every row carries the request, the response hash and the reference so the verdict can be reproduced. Delivery results do not affect scores yet.
No delivery checks yet. They run inside the weekly paid probe.
Classification history
Every classification is kept; the newest row is the current category. Rules match the listing text; the model is consulted only when the rules are unsure.
| When | Category | Confidence | Method | Version | Evidence |
|---|---|---|---|---|---|
| 10h ago | Web search | 80% | llm | v1 | claude-haiku-5-5: The endpoint searches the web for a query, then reads the top pages and returns key passages with sources. It is primarily web research built on search, so web_search fits best, though it also involves page scraping. |
| 20h ago | Web search | 60% | rules | v1 | rule web_search matched "web search" in metadata |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 17m ago | free | 402 | 988 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |
| 7h ago | free | 402 | 520 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |
| 13h ago | free | 402 | 401 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |
| 19h ago | free | 402 | 393 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |
| 25h ago | free | 402 | 329 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |
| 31h ago | free | 402 | 301 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |
| 38h ago | free | 402 | 344 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |