Published finding
hy4-preview@deepinfra: thinking-token use rose on the instruction following probe set
Watch on the daily battery. This model measured against its own witnessed baseline.
1,326 tok→2,505 tok
| model | hy4-preview@deepinfra |
|---|---|
| identity | alias · a floating name the provider may re-point; a change here means what is served under this name changed |
| dimension | Instruction following |
| metric | thinking_tokens_mean |
| decision rule | Relative shift past the watch threshold, unconfirmed |
| first flagged | 2026-11-09 · latest reading |
| coverage | 24 call errors on this reading |
Trace the evidence
The witnessed reading for this date and battery, and the Rekor witness bundle. The full series is in series.json.
This entry records an observation under the stated decision rule. Watches remain unconfirmed; latency is operational context. The instrument does not establish the cause of a change.