{"schemaVersion":1,"available":true,"generatedAt":"2026-08-11T09:42:21.000Z","policy":{"modelCheckIntervalSeconds":21600,"agentCheckIntervalSeconds":604800,"automaticPublishing":true,"automaticMonitorTargetIds":["model-lmarena-text-style-control"],"failClosed":true},"lastRun":{"scheduledAt":"2026-08-11T06:17:00.000Z","completedAt":"2026-08-11T06:32:03.000Z","status":"partial","checkedSourceCount":3,"changedSourceCount":1,"errorSourceCount":1,"publishedSnapshotCount":0,"rejectedSnapshotCount":0},"sources":[{"monitorTargetId":"model-lmarena-text-style-control","publishedSourceIds":["lmarena"],"kind":"model","name":"LMArena · Text Style Control","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/viewer/text_style_control/latest","checkIntervalSeconds":21600,"publicationMode":"validated-automatic","state":"delayed","lastCheckedAt":"2026-08-11T06:31:54.000Z","lastSuccessfulCheckAt":"2026-08-10T00:59:14.000Z","lastObservedContentChangeAt":"2026-08-08T08:04:00.000Z","reviewPending":false,"reviewReason":null},{"monitorTargetId":"model-artificial-analysis","publishedSourceIds":["artificial-analysis"],"kind":"model","name":"Artificial Analysis · Intelligence Index","sourceUrl":"https://artificialanalysis.ai/leaderboards/models","checkIntervalSeconds":21600,"publicationMode":"manual-review","state":"change-detected","lastCheckedAt":"2026-08-11T06:32:02.000Z","lastSuccessfulCheckAt":"2026-08-11T06:32:02.000Z","lastObservedContentChangeAt":"2026-08-11T06:32:02.000Z","reviewPending":true,"reviewReason":"source-change"},{"monitorTargetId":"model-livebench","publishedSourceIds":["livebench"],"kind":"model","name":"LiveBench","sourceUrl":"https://livebench.ai/","checkIntervalSeconds":21600,"publicationMode":"manual-review","state":"change-detected","lastCheckedAt":"2026-08-11T06:32:03.000Z","lastSuccessfulCheckAt":"2026-08-11T06:32:03.000Z","lastObservedContentChangeAt":"2026-08-11T00:27:20.000Z","reviewPending":true,"reviewReason":"source-change"},{"monitorTargetId":"agent-swe-bench-verified","publishedSourceIds":["swe-bench-verified-500"],"kind":"agent","name":"SWE-bench Verified","sourceUrl":"https://www.swebench.com/verified.html","checkIntervalSeconds":604800,"publicationMode":"manual-review","state":"review-required","lastCheckedAt":"2026-08-08T08:04:02.000Z","lastSuccessfulCheckAt":"2026-08-08T08:04:02.000Z","lastObservedContentChangeAt":null,"reviewPending":true,"reviewReason":"baseline-unverified"},{"monitorTargetId":"agent-terminal-bench-2-1","publishedSourceIds":["terminal-bench-2-1"],"kind":"agent","name":"Terminal-Bench 2.1","sourceUrl":"https://www.tbench.ai/leaderboard/terminal-bench/2.1","checkIntervalSeconds":604800,"publicationMode":"manual-review","state":"review-required","lastCheckedAt":"2026-08-08T08:04:02.000Z","lastSuccessfulCheckAt":"2026-08-08T08:04:02.000Z","lastObservedContentChangeAt":null,"reviewPending":true,"reviewReason":"baseline-unverified"},{"monitorTargetId":"agent-hal-assistantbench","publishedSourceIds":["hal-assistantbench-public-33"],"kind":"agent","name":"Holistic Agent Leaderboard · AssistantBench","sourceUrl":"https://hal.cs.princeton.edu/assistantbench","checkIntervalSeconds":604800,"publicationMode":"manual-review","state":"review-required","lastCheckedAt":"2026-08-08T08:04:03.000Z","lastSuccessfulCheckAt":"2026-08-08T08:04:03.000Z","lastObservedContentChangeAt":null,"reviewPending":true,"reviewReason":"baseline-unverified"},{"monitorTargetId":"agent-webarena","publishedSourceIds":["webarena-0-2-0"],"kind":"agent","name":"WebArena","sourceUrl":"https://webarena.dev/","checkIntervalSeconds":604800,"publicationMode":"manual-review","state":"review-required","lastCheckedAt":"2026-08-08T08:04:04.000Z","lastSuccessfulCheckAt":"2026-08-08T08:04:04.000Z","lastObservedContentChangeAt":null,"reviewPending":true,"reviewReason":"baseline-unverified"},{"monitorTargetId":"agent-osworld-2","publishedSourceIds":["osworld-2-2026-06-24-500"],"kind":"agent","name":"OSWorld 2.0","sourceUrl":"https://osworld-v2.xlang.ai/","checkIntervalSeconds":604800,"publicationMode":"manual-review","state":"review-required","lastCheckedAt":"2026-08-08T08:04:05.000Z","lastSuccessfulCheckAt":"2026-08-08T08:04:05.000Z","lastObservedContentChangeAt":null,"reviewPending":true,"reviewReason":"baseline-unverified"},{"monitorTargetId":"agent-bfcl-v4","publishedSourceIds":["bfcl-v4"],"kind":"agent","name":"Berkeley Function-Calling Leaderboard V4","sourceUrl":"https://gorilla.cs.berkeley.edu/leaderboard","checkIntervalSeconds":604800,"publicationMode":"manual-review","state":"review-required","lastCheckedAt":"2026-08-08T08:04:05.000Z","lastSuccessfulCheckAt":"2026-08-08T08:04:05.000Z","lastObservedContentChangeAt":null,"reviewPending":true,"reviewReason":"baseline-unverified"},{"monitorTargetId":"agent-hal-gaia","publishedSourceIds":["hal-gaia-public-validation-165"],"kind":"agent","name":"Holistic Agent Leaderboard · GAIA","sourceUrl":"https://hal.cs.princeton.edu/gaia","checkIntervalSeconds":604800,"publicationMode":"manual-review","state":"review-required","lastCheckedAt":"2026-08-08T08:04:06.000Z","lastSuccessfulCheckAt":"2026-08-08T08:04:06.000Z","lastObservedContentChangeAt":null,"reviewPending":true,"reviewReason":"baseline-unverified"},{"monitorTargetId":"agent-tau-bench","publishedSourceIds":["tau2-bench-1-0-1-base-standard","tau3-banking-1-0-1-alltools"],"kind":"agent","name":"Sierra Research · tau-bench","sourceUrl":"https://github.com/sierra-research/tau2-bench/tree/main/web/leaderboard/public/submissions","checkIntervalSeconds":604800,"publicationMode":"manual-review","state":"review-required","lastCheckedAt":"2026-08-08T08:04:09.000Z","lastSuccessfulCheckAt":"2026-08-08T08:04:09.000Z","lastObservedContentChangeAt":null,"reviewPending":true,"reviewReason":"baseline-unverified"}]}