{ "schemaVersion": 1, "createdAt": "2026-08-22T08:29:48.253Z", "model": "webbrain-browser-vision-tiny-2", "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": 36, "successRate": 0.36, "meanScore": 0.7499122266622266, "meanLatencyMs": 1967.96 }, "byDifficulty": { "easy": { "cases": 20, "scored": 20, "errors": 0, "successes": 12, "successRate": 0.6, "meanScore": 0.8306637806637805, "meanLatencyMs": 1759.85 }, "basic": { "cases": 20, "scored": 20, "errors": 0, "successes": 8, "successRate": 0.4, "meanScore": 0.77874888999889, "meanLatencyMs": 1760.15 }, "intermediate": { "cases": 20, "scored": 20, "errors": 0, "successes": 8, "successRate": 0.4, "meanScore": 0.7956476856476855, "meanLatencyMs": 1829 }, "advanced": { "cases": 20, "scored": 20, "errors": 0, "successes": 2, "successRate": 0.1, "meanScore": 0.6214635364635364, "meanLatencyMs": 1911.45 }, "challenging": { "cases": 20, "scored": 20, "errors": 0, "successes": 6, "successRate": 0.3, "meanScore": 0.7230372405372406, "meanLatencyMs": 2579.35 } }, "byCategory": { "authentication": { "cases": 5, "scored": 5, "errors": 0, "successes": 1, "successRate": 0.2, "meanScore": 0.7618648018648019, "meanLatencyMs": 2116.8 }, "search-results": { "cases": 5, "scored": 5, "errors": 0, "successes": 1, "successRate": 0.2, "meanScore": 0.7787878787878788, "meanLatencyMs": 2410.6 }, "checkout": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.7933177933177933, "meanLatencyMs": 2275 }, "form-validation": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.54, "meanLatencyMs": 1788.2 }, "modal-overlay": { "cases": 5, "scored": 5, "errors": 0, "successes": 1, "successRate": 0.2, "meanScore": 0.8121212121212122, "meanLatencyMs": 2095 }, "toast-notification": { "cases": 5, "scored": 5, "errors": 0, "successes": 3, "successRate": 0.6, "meanScore": 0.7777777777777779, "meanLatencyMs": 1823.8 }, "loading-state": { "cases": 5, "scored": 5, "errors": 0, "successes": 2, "successRate": 0.4, "meanScore": 0.7742424242424242, "meanLatencyMs": 1284.6 }, "consent-banner": { "cases": 5, "scored": 5, "errors": 0, "successes": 1, "successRate": 0.2, "meanScore": 0.6399999999999999, "meanLatencyMs": 1957 }, "dashboard": { "cases": 5, "scored": 5, "errors": 0, "successes": 4, "successRate": 0.8, "meanScore": 0.9, "meanLatencyMs": 2339.8 }, "chart-reading": { "cases": 5, "scored": 5, "errors": 0, "successes": 3, "successRate": 0.6, "meanScore": 0.9, "meanLatencyMs": 1604.4 }, "data-table": { "cases": 5, "scored": 5, "errors": 0, "successes": 3, "successRate": 0.6, "meanScore": 0.7714285714285714, "meanLatencyMs": 1956.2 }, "email-compose": { "cases": 5, "scored": 5, "errors": 0, "successes": 1, "successRate": 0.2, "meanScore": 0.6833333333333333, "meanLatencyMs": 1958.6 }, "kanban-board": { "cases": 5, "scored": 5, "errors": 0, "successes": 4, "successRate": 0.8, "meanScore": 0.8, "meanLatencyMs": 1610.6 }, "calendar": { "cases": 5, "scored": 5, "errors": 0, "successes": 1, "successRate": 0.2, "meanScore": 0.6317460317460318, "meanLatencyMs": 1963.6 }, "map-and-travel": { "cases": 5, "scored": 5, "errors": 0, "successes": 3, "successRate": 0.6, "meanScore": 0.805, "meanLatencyMs": 1541.6 }, "photo-understanding": { "cases": 5, "scored": 5, "errors": 0, "successes": 4, "successRate": 0.8, "meanScore": 0.8666666666666666, "meanLatencyMs": 1398.6 }, "multilingual-ocr": { "cases": 5, "scored": 5, "errors": 0, "successes": 1, "successRate": 0.2, "meanScore": 0.5454545454545453, "meanLatencyMs": 3396.8 }, "occlusion-and-contrast": { "cases": 5, "scored": 5, "errors": 0, "successes": 1, "successRate": 0.2, "meanScore": 0.7, "meanLatencyMs": 1876.8 }, "security-challenge": { "cases": 5, "scored": 5, "errors": 0, "successes": 0, "successRate": 0, "meanScore": 0.6965034965034966, "meanLatencyMs": 1971 }, "uncertainty-calibration": { "cases": 5, "scored": 5, "errors": 0, "successes": 2, "successRate": 0.4, "meanScore": 0.8200000000000001, "meanLatencyMs": 1990.2 } } }