Model
deepseek-chat@deepseek
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 | 82 readings (2026-08-20 to 2026-11-09) Latest assessment: Assessed (7/7 metrics eligible) |
| weekly battery | 14 readings (2026-08-23 to 2026-11-08) Latest assessment: Assessed (7/7 metrics eligible) |
Published findings
Instruction following pass rate fell Movement
100%→60%
Explore
Open the daily dossier · Open the weekly dossier. Each dossier shows this model and battery, with the full dimension history.