Model
hy4-preview@deepinfra
Measured against its own past on the daily and weekly batteries. Each battery has its own history and assessment.
| provider channel | openai_compat |
|---|---|
| identity | alias · a floating name the provider may re-point; a change here means what is served under this name changed |
| daily battery | 45 readings (2026-09-26 to 2026-11-09) Latest assessment: Assessment limited (11/13 metrics eligible) |
| weekly battery | 7 readings (2026-09-27 to 2026-11-08) Latest assessment: Baseline accruing (0/13 metrics eligible) |
Published findings
Thinking-token use rose on the verbosity probe set Movement
372 tok→759 tok
Thinking-token use rose on the instruction following probe set Movement
967 tok→3,028 tok
Thinking-token use rose on the sycophancy probe set Movement
218 tok→1,631 tok
Thinking-token use rose on the instruction following probe set Watch
1,326 tok→2,505 tok
Explore
Open the daily dossier · Open the weekly dossier. Each dossier shows this model and battery, with the full dimension history.