AI Desk · Model Identity

Know what model you're actually using

Benchmarks tell you how good a model is. YFarmX tells you what it is. Independent fingerprints for AI models and endpoints: measured tokenizer signatures, API-surface contracts and lineage evidence, kept as history.

Try:

Models indexed
422
Fingerprinted
158
Tokenizer groups
35
Unlabelled models placed
47 of 108
New since 20 August
4

Catalogue and measurements as at 22 August 2026. Every figure derives from the committed measurement files; the methodology records how, and what the method cannot see.

Live discovery

A stealth model, measured while its identity stays undeclared

Ox Alpha

stealth/ox-alpha · Undisclosed (stealth)Family resolved by measurement
Likely family (measured)
Z.ai
Identity confidence
Very high
Declared tokenizer tag
Other
Entered catalogue
20 August 2026
Last tested
21 August 2026
Measurement
Measured
Evidence
  • exact tokenizer signature shared with 2 models
  • API-surface contract identical to a group member

What the measurements say

Findings the current dataset supports

Explore

How it works

01 · MEASURE

Fifty adversarial strings are sent to each model and only the reported prompt-token count is read. The marginal cost of each string under the model's tokenizer becomes a 50-number signature.

02 · COMPARE

Signatures are compared offline against every other model measured. Exact agreement across all fifty strings is strong lineage evidence; the API-surface contract is checked as an independent second signal.

03 · TRACK

Every observation is kept, none is overwritten. When an endpoint's fingerprint moves, the history shows what changed and on which day.

A shared tokenizer is evidence of shared lineage, never proof of an exact model. Theclaims hierarchy keeps every published conclusion inside what the evidence supports, and the controls are published with the results.