🇯🇵 JP Model Bench

Compare aisubscription (GLM pool) vs fugu-ultra (Sakana) on frozen JP fixtures. Runs dispatch the real refresh pipeline via Horizon.

Orchestrator status

Loading…

Run comparison

Use aisubscription for GLM pool, fugu-ultra for Sakana.

JP fixtures (10)

jp-1 jp-10 jp-2 jp-3 jp-4 jp-5 jp-6 jp-7 jp-8 jp-9

Recent runs (Mongo)

Name Status Winner Cost
grid-anthropic-claude-sonnet-5-jp-1-rescore-status completed $0.0000

Artifacts on disk

Run ID Updated
6a7eef8779d96d8c310a1d4b 1 month ago Open
6a7dd0e26a46b4f79e0777eb 1 month ago Open
6a7dba33930569d92c0ca93b 1 month ago Open
6a7db368046b79c3cf0f0cab 1 month ago Open
6a7db0078c0925cf5703299b 1 month ago Open
6a70675f8caa70db9b02fb55 1 month ago Open
6a54b9b53c5a69040b095eef 2 months ago Open
6a54b8e23c5a69040b095ee8 2 months ago Open
6a54b8043c5a69040b095ee1 2 months ago Open
6a54b6c43c5a69040b095eda 2 months ago Open
6a54b5493c5a69040b095ed3 2 months ago Open
6a54ab6c3c5a69040b095ec1 2 months ago Open
6a54a9853c5a69040b095eba 2 months ago Open
6a54a7ce3c5a69040b095eb3 2 months ago Open
6a54a67d3c5a69040b095eac 2 months ago Open
6a54a4e73c5a69040b095ea5 2 months ago Open
6a54a3bd3c5a69040b095e9e 2 months ago Open
6a54992d3c5a69040b095e8c 2 months ago Open
6a5499213c5a69040b095e85 2 months ago Open
6a511e25d5d870a3340f1848 2 months ago Open