Model
gpt-6-luna
Measured against its own past on the daily and weekly batteries. Each battery has its own history and assessment.
| provider channel | openai |
|---|---|
| identity | alias · a floating name the provider may re-point; a change here means what is served under this name changed |
| daily battery | 46 readings (2026-09-25 to 2026-11-09) Latest assessment: Assessed (13/13 metrics eligible) |
| weekly battery | 8 readings (2026-09-25 to 2026-11-08) Latest assessment: Assessed (13/13 metrics eligible) |
Published findings
Thinking-token use fell on the structured output probe set Movement
2 tok→0 tok
Thinking-token use rose on the instruction following probe set Movement
2 tok→8 tok
Thinking-token use rose on the sycophancy probe set Movement
5 tok→28 tok
Explore
Open the daily dossier · Open the weekly dossier. Each dossier shows this model and battery, with the full dimension history.