Operator log · the archive
Every day, frozen, cited, and inspectable.
The Intelligent Router refreshes its model-landscape snapshot once every twenty-four hours. Each refresh produces a dated rundown — what BurnBar would have recommended that day, the sources it cited, the freshness of every signal, and the limitations of every claim. Nothing is overwritten. Future humans can verify what was said.
- 3 dated rundowns
- newest · 2026-05-13
- oldest · 2026-05-11
Benchmark signals are advisory. Each rundown shows what the daily snapshot said, not what the router actually ran — provider-family mode, user pinning, account auth, quota state, safety policy, and availability all override these recommendations at runtime. Use this archive to inspect why a given recommendation was made, not as proof a given route was executed.
Sources we cite
Each daily rundown attributes its claims back to a documented public source. Citations carry logos so operators can audit provenance at a glance. We never fabricate benchmark numbers, scrape authenticated dashboards, or persist API keys inside snapshots.
-
Artificial Analysis AAIndependent intelligence + coding indices, pricing, and TPS/TTFT samples.
artificialanalysis.ai/ → -
Terminal-Bench (via Hugging Face) TBPublic Terminal-Bench leaderboard, verified runs weighted higher.
www.tbench.ai/ → -
Design Arena DAPairwise design-task evals with Elo + win-rate, by arena and category.
www.designarena.ai/ → -
-
Manual OpenBurnBar fixture OBBCached / hand-curated snapshot for sources without a live API.
/router#sources →