{ "schemaVersion": 1, "createdAt": "2026-08-21T17:46:56.876Z", "model": "lfm25-vl-450m-base", "endpoint": "http://127.0.0.1:8000/v1/chat/completions", "promptMode": "production", "productionUserText": "Describe this screenshot of the current browser viewport for a web-automation agent. Follow the format in the system prompt.", "promptSha256": "8465a0e60af8f3e4dcc5ff188a7682c22b1d52974db54ccb42ff8a1a5346a207", "overall": { "cases": 100, "scored": 100, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.04171031746031747, "meanLatencyMs": 560.82 }, "byDifficulty": { "easy": { "cases": 20, "scored": 20, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.05486111111111112, "meanLatencyMs": 461.15 }, "basic": { "cases": 20, "scored": 20, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.06378968253968254, "meanLatencyMs": 399.85 }, "intermediate": { "cases": 20, "scored": 20, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.05128968253968254, "meanLatencyMs": 899.75 }, "advanced": { "cases": 20, "scored": 20, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.02361111111111111, "meanLatencyMs": 592.35 }, "challenging": { "cases": 20, "scored": 20, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.015, "meanLatencyMs": 451 } }, "byCategory": { "authentication": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 619 }, "search-results": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 392.6 }, "checkout": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 448.2 }, "form-validation": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 377.4 }, "modal-overlay": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 330.4 }, "toast-notification": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 337.8 }, "loading-state": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 339.4 }, "consent-banner": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 477.4 }, "dashboard": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 542.8 }, "chart-reading": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.2, "meanLatencyMs": 391.6 }, "data-table": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.08571428571428572, "meanLatencyMs": 654.4 }, "email-compose": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 1022 }, "kanban-board": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.08571428571428572, "meanLatencyMs": 436.6 }, "calendar": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 455 }, "map-and-travel": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.28500000000000003, "meanLatencyMs": 428.8 }, "photo-understanding": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.17777777777777776, "meanLatencyMs": 2387 }, "multilingual-ocr": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 398 }, "occlusion-and-contrast": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 359.8 }, "security-challenge": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 476 }, "uncertainty-calibration": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0, "meanLatencyMs": 342.2 } } }