Leaderboard / money-reactor.makar52nn2016.workers.dev / endpoint
GET https://money-reactor.makar52nn2016.workers.dev/api/ai-extract
Scores measure reliability and honesty, not output quality.
- The payment wallet changed in the last 7 days, which caps the verdict at caution until it has been stable for a week.
- Quoted a price different from the listed price on 8 of 8 comparable probes.
- Category
- Web scrape by llm, confidence 62%
- Latest quote
- $0.5 on Base to 0xF7f2…1baD
- Uptime
- 100% / 7d, 100% / 30d
- Delivery
- none not yet paid-tested
- Observed
- none reported yet (opt-in wrapper telemetry)
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 6h ago
- Next probe
- 2026-11-18 05:38 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.1 | 0xf47b…512E | default | yes | 1h ago |
| payai | exact | Base | 0x8335…2913 | $0.1 | 0xf47b…512E | default | yes | 48m 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. Judged results feed the "Delivery after payment" component (pass 1, error after payment 0.25, fail 0); inconclusive rows are excluded; a fail in the last 14 days caps the verdict at caution. Methodology.
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 |
|---|---|---|---|---|---|
| 29h ago | Web scrape | 62% | llm | v1 | claude-haiku-5-5: The endpoint reads a supplied web page and answers a question about it via an LLM. The core returned value is page-derived content, which points to web_scrape, though the LLM question-answering could suggest inference. Scraping is the primary function. |
| 32h ago | Inference | 60% | rules | v1 | rule inference matched "llm" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 6h ago | free | 402 | 213 ms | v2 | yes | $0.5 | 0xF7f2…1baD | price_above_listingprice_mismatchpayto_mismatch |
| 13h ago | free | 402 | 46 ms | v2 | yes | $0.5 | 0xF7f2…1baD | price_above_listingprice_mismatchpayto_mismatch |
| 19h ago | free | 402 | 315 ms | v2 | yes | $0.5 | 0xF7f2…1baD | price_above_listingprice_mismatchpayto_mismatch |
| 25h ago | free | 402 | 341 ms | v2 | yes | $0.5 | 0xF7f2…1baD | price_above_listingprice_mismatchpayto_mismatch |
| 32h ago | free | 402 | 255 ms | v2 | yes | $0.5 | 0xF7f2…1baD | price_above_listingprice_mismatchpayto_mismatch |
| 38h ago | free | 402 | 179 ms | v2 | yes | $0.5 | 0xF7f2…1baD | price_above_listingprice_mismatchpayto_mismatch |
| 44h ago | free | 402 | 557 ms | v2 | yes | $0.5 | 0xF7f2…1baD | price_above_listingprice_mismatchpayto_mismatchpayto_changed |
| 2d ago | free | 402 | 19 ms | v2 | yes | $0.5 | 0x4Ce5…79C9 | price_above_listingprice_mismatchpayto_mismatch |