model
Mistral Large 4 llm
A model record: onboarded once for the project and used by any eval's arms.
- aliases
eval-mistral-large-4- settings
reasoning_effortlow its provider refused reasoning_effort none (onboarding, 2026-10-31); low is the least it is asked- onboarding
- vetted 2026-10-31
- best result per goal
- #38 of 55 Triage decisions on Orrery's error signals
01deployments and their onboarding
hosted · homelab LiteLLM (the fleet's gateway) · eval-mistral-large-4 · onboarding pass 2026-10-31 · 129.7 tokens/s · 1 accepted
- where
- homelab LiteLLM (the fleet's gateway)
- build
eval-mistral-large-4- 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-mistral-large-4 | — |
| digest found | None | — |
| default | s 2.33 · tokens out 263 · reasoned: yes · finish stop | — |
| chosen | s 2.03 · tokens out 263 · reasoned: yes · finish stop · settings (reasoning effort low) | — |
| tokens per s | 129.7 | — |
| deterministic | yes | — |
| json valid | yes | — |
Accepted: reasoning: it still reasons with the record's settings (its provider refuses reasoning_effort none and it still reasons with low (onboarding, 2026-10-31); low is the least)
What it can do, across its deployments: reasons: yes · json mode: yes · reasoning off 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 |
| 2026-10-31 | reasoning_effort: none → low | its provider refused reasoning_effort none (onboarding, 2026-10-31); low is the least it is asked |
03arms
| arm | deployment | goal | its settings | arm smoke | result |
|---|---|---|---|---|---|
| triage_mistral_large_4_v1 · rescored 5f2c057c orrery_triage_v1_labelled | hosted | Triage decisions on Orrery's error signals | — | none | triage_cost 0.800 |
| triage_mistral_large_4_v2 · rescored 5f2c057c orrery_triage_v1_labelled | hosted | Triage decisions on Orrery's error signals | max_tokens 4096 | pass 2026-10-31 | triage_cost 0.800 |