Files
windmill/ai_evals/history/flow.jsonl

4 lines
10 KiB
JSON

{"createdAt":"2026-04-10T14:25:16.664Z","gitSha":"8f8b487be517a0bdd318c36857c1d46d5ab0723a","mode":"flow","runs":1,"runModel":"anthropic:claude-haiku-4-5-20251001","judgeModel":"claude-sonnet-4-6","caseCount":13,"attemptCount":13,"passedAttempts":8,"passRate":0.6153846153846154,"averageDurationMs":33424.692307692305,"averageJudgeScore":82.61538461538461,"averageTokenUsagePerAttempt":{"prompt":131901,"completion":3121.230769230769,"total":135022.23076923078},"failedCaseIds":["flow-test6-ai-agent-tools","flow-test7-simple-modification","flow-test9-parallel-refactor","flow-test10-while-loop-counter","flow-test11-preprocessor-and-failure-handler"],"cases":[{"id":"flow-test0-sum-two-numbers","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":16943,"averageJudgeScore":98,"averageTokenUsagePerAttempt":{"prompt":126615,"completion":839,"total":127454}},{"id":"flow-test1-reuse-existing-script","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":15220,"averageJudgeScore":100,"averageTokenUsagePerAttempt":{"prompt":75614,"completion":805,"total":76419}},{"id":"flow-test2-call-existing-subflow","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":15699,"averageJudgeScore":97,"averageTokenUsagePerAttempt":{"prompt":76182,"completion":887,"total":77069}},{"id":"flow-test3-branchone-routing","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":21605,"averageJudgeScore":100,"averageTokenUsagePerAttempt":{"prompt":62230,"completion":1509,"total":63739}},{"id":"flow-test4-order-processing-loop","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":47228,"averageJudgeScore":97,"averageTokenUsagePerAttempt":{"prompt":143511,"completion":5443,"total":148954}},{"id":"flow-test5-parallel-data-pipeline","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":81870,"averageJudgeScore":92,"averageTokenUsagePerAttempt":{"prompt":194542,"completion":12409,"total":206951}},{"id":"flow-test6-ai-agent-tools","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":51878,"averageJudgeScore":72,"averageTokenUsagePerAttempt":{"prompt":142071,"completion":5720,"total":147791}},{"id":"flow-test7-simple-modification","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":49113,"averageJudgeScore":42,"averageTokenUsagePerAttempt":{"prompt":318525,"completion":2702,"total":321227}},{"id":"flow-test8-branching-in-loop","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":18244,"averageJudgeScore":82,"averageTokenUsagePerAttempt":{"prompt":78441,"completion":979,"total":79420}},{"id":"flow-test9-parallel-refactor","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":49485,"averageJudgeScore":72,"averageTokenUsagePerAttempt":{"prompt":135237,"completion":5467,"total":140704}},{"id":"flow-test10-while-loop-counter","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":21210,"averageJudgeScore":90,"averageTokenUsagePerAttempt":{"prompt":127844,"completion":1179,"total":129023}},{"id":"flow-test11-preprocessor-and-failure-handler","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":25142,"averageJudgeScore":42,"averageTokenUsagePerAttempt":{"prompt":128648,"completion":1337,"total":129985}},{"id":"flow-test12-approval-step","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":20884,"averageJudgeScore":90,"averageTokenUsagePerAttempt":{"prompt":105253,"completion":1300,"total":106553}}]}
{"createdAt":"2026-04-10T14:57:17.513Z","gitSha":"2a58402cfc5c320748839e92b51a1291b937bf26","mode":"flow","runs":1,"runModel":"anthropic:claude-opus-4-6","judgeModel":"claude-sonnet-4-6","caseCount":13,"attemptCount":13,"passedAttempts":8,"passRate":0.6153846153846154,"averageDurationMs":58074.53846153846,"averageJudgeScore":87.53846153846153,"averageTokenUsagePerAttempt":{"prompt":125452.76923076923,"completion":2957.769230769231,"total":128410.53846153847},"failedCaseIds":["flow-test4-order-processing-loop","flow-test6-ai-agent-tools","flow-test7-simple-modification","flow-test10-while-loop-counter","flow-test11-preprocessor-and-failure-handler"],"cases":[{"id":"flow-test0-sum-two-numbers","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":26967,"averageJudgeScore":97,"averageTokenUsagePerAttempt":{"prompt":103796,"completion":634,"total":104430}},{"id":"flow-test1-reuse-existing-script","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":29009,"averageJudgeScore":100,"averageTokenUsagePerAttempt":{"prompt":75507,"completion":743,"total":76250}},{"id":"flow-test2-call-existing-subflow","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":26828,"averageJudgeScore":100,"averageTokenUsagePerAttempt":{"prompt":76172,"completion":807,"total":76979}},{"id":"flow-test3-branchone-routing","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":44418,"averageJudgeScore":100,"averageTokenUsagePerAttempt":{"prompt":130440,"completion":1787,"total":132227}},{"id":"flow-test4-order-processing-loop","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":82185,"averageJudgeScore":97,"averageTokenUsagePerAttempt":{"prompt":116133,"completion":4905,"total":121038}},{"id":"flow-test5-parallel-data-pipeline","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":110344,"averageJudgeScore":97,"averageTokenUsagePerAttempt":{"prompt":122092,"completion":6980,"total":129072}},{"id":"flow-test6-ai-agent-tools","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":119901,"averageJudgeScore":72,"averageTokenUsagePerAttempt":{"prompt":154916,"completion":8908,"total":163824}},{"id":"flow-test7-simple-modification","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":44333,"averageJudgeScore":72,"averageTokenUsagePerAttempt":{"prompt":109935,"completion":1536,"total":111471}},{"id":"flow-test8-branching-in-loop","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":54247,"averageJudgeScore":97,"averageTokenUsagePerAttempt":{"prompt":136872,"completion":2638,"total":139510}},{"id":"flow-test9-parallel-refactor","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":63274,"averageJudgeScore":82,"averageTokenUsagePerAttempt":{"prompt":137794,"completion":3686,"total":141480}},{"id":"flow-test10-while-loop-counter","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":38813,"averageJudgeScore":82,"averageTokenUsagePerAttempt":{"prompt":105075,"completion":1157,"total":106232}},{"id":"flow-test11-preprocessor-and-failure-handler","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":77267,"averageJudgeScore":52,"averageTokenUsagePerAttempt":{"prompt":256547,"completion":3398,"total":259945}},{"id":"flow-test12-approval-step","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":37383,"averageJudgeScore":90,"averageTokenUsagePerAttempt":{"prompt":105607,"completion":1272,"total":106879}}]}
{"createdAt":"2026-04-10T14:29:52.249Z","gitSha":"8f8b487be517a0bdd318c36857c1d46d5ab0723a","mode":"flow","runs":1,"runModel":"openai:gpt-4o","judgeModel":"claude-sonnet-4-6","caseCount":13,"attemptCount":13,"passedAttempts":6,"passRate":0.46153846153846156,"averageDurationMs":29841.53846153846,"averageJudgeScore":68.46153846153847,"averageTokenUsagePerAttempt":{"prompt":72815.92307692308,"completion":770.7692307692307,"total":73586.69230769231},"failedCaseIds":["flow-test5-parallel-data-pipeline","flow-test6-ai-agent-tools","flow-test7-simple-modification","flow-test9-parallel-refactor","flow-test10-while-loop-counter","flow-test11-preprocessor-and-failure-handler","flow-test12-approval-step"],"cases":[{"id":"flow-test0-sum-two-numbers","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":20059,"averageJudgeScore":97,"averageTokenUsagePerAttempt":{"prompt":64091,"completion":265,"total":64356}},{"id":"flow-test1-reuse-existing-script","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":20728,"averageJudgeScore":100,"averageTokenUsagePerAttempt":{"prompt":46594,"completion":270,"total":46864}},{"id":"flow-test2-call-existing-subflow","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":21533,"averageJudgeScore":98,"averageTokenUsagePerAttempt":{"prompt":46859,"completion":232,"total":47091}},{"id":"flow-test3-branchone-routing","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":29004,"averageJudgeScore":100,"averageTokenUsagePerAttempt":{"prompt":64593,"completion":568,"total":65161}},{"id":"flow-test4-order-processing-loop","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":36250,"averageJudgeScore":95,"averageTokenUsagePerAttempt":{"prompt":66346,"completion":1259,"total":67605}},{"id":"flow-test5-parallel-data-pipeline","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":46151,"averageJudgeScore":72,"averageTokenUsagePerAttempt":{"prompt":104676,"completion":1698,"total":106374}},{"id":"flow-test6-ai-agent-tools","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":72403,"averageJudgeScore":62,"averageTokenUsagePerAttempt":{"prompt":105280,"completion":2216,"total":107496}},{"id":"flow-test7-simple-modification","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":41599,"averageJudgeScore":20,"averageTokenUsagePerAttempt":{"prompt":103053,"completion":707,"total":103760}},{"id":"flow-test8-branching-in-loop","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":23352,"averageJudgeScore":82,"averageTokenUsagePerAttempt":{"prompt":97955,"completion":468,"total":98423}},{"id":"flow-test9-parallel-refactor","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":19341,"averageJudgeScore":0,"averageTokenUsagePerAttempt":{"prompt":12254,"completion":1057,"total":13311}},{"id":"flow-test10-while-loop-counter","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":16143,"averageJudgeScore":82,"averageTokenUsagePerAttempt":{"prompt":64480,"completion":445,"total":64925}},{"id":"flow-test11-preprocessor-and-failure-handler","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":24231,"averageJudgeScore":52,"averageTokenUsagePerAttempt":{"prompt":106068,"completion":472,"total":106540}},{"id":"flow-test12-approval-step","attemptCount":1,"passedAttempts":0,"passRate":0,"averageDurationMs":17146,"averageJudgeScore":30,"averageTokenUsagePerAttempt":{"prompt":64358,"completion":363,"total":64721}}]}