Leaderboard / agentdata-api.sander-van-aard.workers.dev / endpoint
POST https://agentdata-api.sander-van-aard.workers.dev/media/transcribe
Scores measure reliability and honesty, not output quality.
- 4 probes got a response that was not a 402 payment challenge.
- Listed only 2 days ago; new listings earn trust over 30 days.
- Category
- Document by llm, confidence 35%
- Latest quote
- — on — to —
- 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
- 4h ago
- Next probe
- 2026-11-19 02:20 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|
Listing changes
| When | Event | From | To |
|---|---|---|---|
| 29h ago | disappeared | — | — |
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 |
|---|---|---|---|---|---|
| 28h ago | Document | 35% | llm | v1 | claude-haiku-5-5: The path /media/transcribe suggests audio transcription, which falls under document (transcription). The listing has no description, service name, or tags, so confidence is low. |
| 28h ago | Inference | 50% | rules | v1 | rule inference matched "transcribe" in metadata |
| 34h ago | Document | 80% | llm | v1 | claude-haiku-5-5: Speech-to-text transcription of audio files into transcripts and WebVTT subtitles is closest to the document category, which covers transcription and file conversion. It could arguably be inference, but the listing centers on transcribing an uploaded media file rather than model-generated text. |
| 2d ago | Inference | 60% | rules | v1 | rule inference matched "speech to text" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 4h ago | free | 400 | 31 ms | — | no | — | — | unexpected_status:400status_not_402 |
| 11h ago | free | 400 | 26 ms | — | no | — | — | unexpected_status:400status_not_402 |
| 18h ago | free | 400 | 14 ms | — | no | — | — | unexpected_status:400status_not_402 |
| 24h ago | free | 400 | 181 ms | — | no | — | — | unexpected_status:400status_not_402 |
| 30h ago | free | 402 | 589 ms | v2 | yes | $0.3 | 0xb0ae…2099 | — |
| 37h ago | free | 402 | 47 ms | v2 | yes | $0.3 | 0xb0ae…2099 | — |
| 43h ago | free | 402 | 153 ms | v2 | yes | $0.3 | 0xb0ae…2099 | — |
| 2d ago | free | 402 | 172 ms | v2 | yes | $0.3 | 0xb0ae…2099 | — |
| 2d ago | free | 402 | 156 ms | v2 | yes | $0.3 | 0xb0ae…2099 | — |
| 3d ago | free | 402 | 29 ms | v2 | yes | $0.3 | 0xb0ae…2099 | — |
| 3d ago | free | 402 | 19 ms | v2 | yes | $0.3 | 0xb0ae…2099 | — |