Files
windmill/ai_evals/history/script.jsonl
2026-04-13 14:05:46 +02:00

4 lines
1.8 KiB
JSON

{"createdAt":"2026-04-10T14:23:51.580Z","gitSha":"8f8b487be517a0bdd318c36857c1d46d5ab0723a","mode":"script","runs":1,"runModel":"anthropic:claude-haiku-4-5-20251001","judgeModel":"claude-sonnet-4-6","caseCount":1,"attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":12112,"averageJudgeScore":100,"averageTokenUsagePerAttempt":{"prompt":48134,"completion":452,"total":48586},"failedCaseIds":[],"cases":[{"id":"script-test1-greet-user","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":12112,"averageJudgeScore":100,"averageTokenUsagePerAttempt":{"prompt":48134,"completion":452,"total":48586}}]}
{"createdAt":"2026-04-10T14:24:18.129Z","gitSha":"8f8b487be517a0bdd318c36857c1d46d5ab0723a","mode":"script","runs":1,"runModel":"anthropic:claude-opus-4-6","judgeModel":"claude-sonnet-4-6","caseCount":1,"attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":16595,"averageJudgeScore":100,"averageTokenUsagePerAttempt":{"prompt":38264,"completion":254,"total":38518},"failedCaseIds":[],"cases":[{"id":"script-test1-greet-user","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":16595,"averageJudgeScore":100,"averageTokenUsagePerAttempt":{"prompt":38264,"completion":254,"total":38518}}]}
{"createdAt":"2026-04-10T14:24:41.534Z","gitSha":"8f8b487be517a0bdd318c36857c1d46d5ab0723a","mode":"script","runs":1,"runModel":"openai:gpt-4o","judgeModel":"claude-sonnet-4-6","caseCount":1,"attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":13643,"averageJudgeScore":97,"averageTokenUsagePerAttempt":{"prompt":28961,"completion":137,"total":29098},"failedCaseIds":[],"cases":[{"id":"script-test1-greet-user","attemptCount":1,"passedAttempts":1,"passRate":1,"averageDurationMs":13643,"averageJudgeScore":97,"averageTokenUsagePerAttempt":{"prompt":28961,"completion":137,"total":29098}}]}