Published finding
deepseek-reasoner@deepseek: tool call pass rate fell
Movement on the weekly battery. This model measured against its own witnessed baseline.
100%→85%
| model | deepseek-reasoner@deepseek |
|---|---|
| identity | alias · a floating name the provider may re-point; a change here means what is served under this name changed |
| dimension | Tool call |
| metric | pass_rate |
| decision rule | Survives Benjamini-Hochberg FDR at α=0.01 |
| first flagged | 2026-10-25 · latest reading |
| coverage | 0 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.