Leaderboard / mentionforge.mentionforge.workers.dev / endpoint
POST https://mentionforge.mentionforge.workers.dev/v1/research
Scores measure reliability and honesty, not output quality.
- Listed only 1 day ago; new listings earn trust over 30 days.
- Answered all 5 probes in the last 7 days.
- Category
- Web search by llm, confidence 80%
- Latest quote
- $0.02 on Base to 0xBe57…8F77
- Uptime
- 100% / 7d, 100% / 30d
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 3h ago
- Next probe
- 2026-11-17 10:13 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.02 | 0xBe57…8F77 | default | yes | 7h 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 |
|---|---|---|---|---|---|
| 6h ago | Web search | 80% | llm | v1 | claude-haiku-5-5: The endpoint returns cited social media mentions, volume, sentiment and themes for a brand, which is social listening over web and social sources. web_search covers search over the web, news or social media, and the description explicitly steers away from generic web search. Sentiment analysis adds some ambiguity, but the core output is mention retrieval rather than a trading signal or model-generated report. |
| 9h ago | Inference | 60% | rules | v1 | rule inference matched "sentiment analysis" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 3h ago | free | 402 | 354 ms | v2 | yes | $0.02 | 0xBe57…8F77 | — |
| 9h ago | free | 402 | 263 ms | v2 | yes | $0.02 | 0xBe57…8F77 | — |
| 15h ago | free | 402 | 352 ms | v2 | yes | $0.02 | 0xBe57…8F77 | — |
| 21h ago | free | 402 | 51 ms | v2 | yes | $0.02 | 0xBe57…8F77 | — |
| 28h ago | free | 402 | 254 ms | v2 | yes | $0.02 | 0xBe57…8F77 | — |