model
GPT-6 Luna llm
A model record: onboarded once for the project and used by any eval's arms.
- weights
- proprietary
- aliases
eval-gpt-6-luna- settings
reasoning_effortnone it reasoned by default on the onboarding probe (2026-10-31); off unless a task needs it (RUNBOOK §16): left at the server's default, one model reasons at length and the next not at all- onboarding
- vetted 2026-10-31
- best result per goal
- #7 of 55 Triage decisions on Orrery's error signals
01deployments and their onboarding
hosted · homelab LiteLLM (the fleet's gateway) · eval-gpt-6-luna · onboarding pass 2026-10-31 · 15.7 tokens/s · 2 accepted
- where
- homelab LiteLLM (the fleet's gateway)
- build
eval-gpt-6-luna- matches the record
- yes
- checked
- 2026-10-31
- onboarded on
- homelab LiteLLM (the fleet's gateway)
| probe | measurement | flag |
|---|---|---|
| endpoint | provider litellm · base url http://homelab:4001/v1 · model eval-gpt-6-luna | — |
| digest found | None | — |
| default | s 2.94 · tokens out 51 · reasoned: yes · finish stop | — |
| chosen | s 1.66 · tokens out 26 · reasoned: no · finish stop · settings (reasoning effort none) | — |
| tokens per s | 15.7 | — |
| deterministic | yes | — |
| json valid | yes | — |
Accepted: where it ran: a hosted gateway serves the provider's current build; there is no digest, revision or hash to pin; determinism: a hosted provider batches requests, so temperature 0 does not repeat exactly; repeats measure it
What it can do, across its deployments: reasons: yes · json mode: yes · reasoning off reasoning_effort: none
02settings history
| when | what changed | why |
|---|---|---|
| 2026-10-31 | reasoning_effort: (server default) → none | it reasoned by default on the onboarding probe (2026-10-31); off unless a task needs it (RUNBOOK §16): left at the server's default, one model reasons at length and the next not at all |
03arms
| arm | deployment | goal | its settings | arm smoke | result |
|---|---|---|---|---|---|
| triage_gpt_6_luna_v1 · rescored 5f2c057c, repeats ×3 orrery_triage_v1_labelled | hosted | Triage decisions on Orrery's error signals | — | none | triage_cost 0.626 |
| triage_gpt_6_luna_v1 · rescored 5f2c057c orrery_triage_v1_labelled | hosted | Triage decisions on Orrery's error signals | — | none | triage_cost 0.585 |
| triage_gpt_6_luna_v2 · rescored 5f2c057c orrery_triage_v1_labelled | hosted | Triage decisions on Orrery's error signals | max_tokens 1024 | pass 2026-10-31 | triage_cost 0.554 |