{
 "schemaVersion": "blobfish.webbench-suite-runs.v1",
 "observedAt": "2026-09-19T09:12:06Z",
 "runs": [
  {
   "benchmarkId": "webbench-fetch",
   "suite": "fetch",
   "runId": "webbench-fetch-tinyfish-20260919-r4",
   "startedAt": "2026-09-19T08:52:08Z",
   "finishedAt": "2026-09-19T09:05:06Z",
   "vendor": {
    "name": "TinyFish",
    "product": "Fetch API",
    "endpoint": "https://api.fetch.tinyfish.ai",
    "configuration": "documented defaults, markdown, ttl 0"
   },
   "harness": "webbench.fetch_bench (hosted protocol, public tunnel)",
   "selection": "All 96 generated pages (record, article and table pages through five chrome profiles), one request per page, no retries, same sitting as every other fetcher in this section.",
   "disclosure": "Pages are generated from a WebBench world and served through a throw-away public tunnel; the generator knows every content unit it emitted. Pass = usable page: content recall ≥ 0.9 and signal ratio ≥ 0.3 (TinyFish's own usability floor). Score = content F1, the harmonic mean of content recall and signal ratio, so neither a clean stub nor a full-page dump scores well. A provider error counts as 0. No LLM judge. Profiles: clean, heavy chrome, consent overlay, client-side rendered, late content.",
   "metric": {
    "label": "Content F1",
    "higherIsBetter": true
   },
   "aggregate": {
    "tasks": 96,
    "attempted": 96,
    "graded": 96,
    "passed": 46,
    "errors": 0,
    "meanScore": 0.4834,
    "latencyMsP50": 1850.4,
    "costUsdTotal": 0.0
   },
   "reference": [
    {
     "name": "Chromium, rendered <main> text 2 s after load (reference ceiling, not ranked)",
     "passed": 96,
     "meanScore": 1.0
    },
    {
     "name": "raw HTML with tags stripped, no rendering (floor, not ranked)",
     "passed": 36,
     "meanScore": 0.5187
    }
   ],
   "trials": [
    {
     "taskId": "p000-record-clean",
     "passed": true,
     "score": 0.9439,
     "latencyMs": 2254.4386189983925,
     "error": null
    },
    {
     "taskId": "p001-article-clean",
     "passed": true,
     "score": 0.9692,
     "latencyMs": 2262.6422960020136,
     "error": null
    },
    {
     "taskId": "p002-table-clean",
     "passed": true,
     "score": 0.9486,
     "latencyMs": 2357.0403090052423,
     "error": null
    },
    {
     "taskId": "p003-docs-clean",
     "passed": true,
     "score": 0.9569,
     "latencyMs": 2158.3578379941173,
     "error": null
    },
    {
     "taskId": "p004-pricing-clean",
     "passed": true,
     "score": 0.9455,
     "latencyMs": 2314.5480079983827,
     "error": null
    },
    {
     "taskId": "p005-news-clean",
     "passed": true,
     "score": 0.9569,
     "latencyMs": 2141.6562399972463,
     "error": null
    },
    {
     "taskId": "p006-record-heavy_chrome",
     "passed": true,
     "score": 0.9606,
     "latencyMs": 2161.223963004886,
     "error": null
    },
    {
     "taskId": "p007-article-heavy_chrome",
     "passed": true,
     "score": 0.9758,
     "latencyMs": 2243.2549510049284,
     "error": null
    },
    {
     "taskId": "p008-table-heavy_chrome",
     "passed": true,
     "score": 0.9447,
     "latencyMs": 2214.5942819988704,
     "error": null
    },
    {
     "taskId": "p009-docs-heavy_chrome",
     "passed": true,
     "score": 0.951,
     "latencyMs": 2295.8426350014633,
     "error": null
    },
    {
     "taskId": "p010-pricing-heavy_chrome",
     "passed": true,
     "score": 0.9553,
     "latencyMs": 1007.7214999982971,
     "error": null
    },
    {
     "taskId": "p011-news-heavy_chrome",
     "passed": true,
     "score": 0.9396,
     "latencyMs": 1261.3840609992621,
     "error": null
    },
    {
     "taskId": "p012-record-consent_overlay",
     "passed": true,
     "score": 0.939,
     "latencyMs": 1194.0776479968918,
     "error": null
    },
    {
     "taskId": "p013-article-consent_overlay",
     "passed": true,
     "score": 0.9689,
     "latencyMs": 1108.539260996622,
     "error": null
    },
    {
     "taskId": "p014-table-consent_overlay",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1221.1667699957616,
     "error": null
    },
    {
     "taskId": "p015-docs-consent_overlay",
     "passed": true,
     "score": 0.9437,
     "latencyMs": 1113.9327100027003,
     "error": null
    },
    {
     "taskId": "p016-pricing-consent_overlay",
     "passed": true,
     "score": 0.9556,
     "latencyMs": 1169.893605998368,
     "error": null
    },
    {
     "taskId": "p017-news-consent_overlay",
     "passed": true,
     "score": 0.9596,
     "latencyMs": 1231.1317880012211,
     "error": null
    },
    {
     "taskId": "p018-record-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1182.2562710003695,
     "error": null
    },
    {
     "taskId": "p019-article-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1258.2451659982326,
     "error": null
    },
    {
     "taskId": "p020-table-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 2284.0677269996377,
     "error": null
    },
    {
     "taskId": "p021-docs-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 2296.8552299935254,
     "error": null
    },
    {
     "taskId": "p022-pricing-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 2262.713750002149,
     "error": null
    },
    {
     "taskId": "p023-news-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 2304.1382290030015,
     "error": null
    },
    {
     "taskId": "p024-record-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 2277.6845330008655,
     "error": null
    },
    {
     "taskId": "p025-article-lazy",
     "passed": false,
     "score": 0.6389,
     "latencyMs": 2292.700057005277,
     "error": null
    },
    {
     "taskId": "p026-table-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 2284.928442000819,
     "error": null
    },
    {
     "taskId": "p027-docs-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 2308.733119003591,
     "error": null
    },
    {
     "taskId": "p028-pricing-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 2268.1730309996055,
     "error": null
    },
    {
     "taskId": "p029-news-lazy",
     "passed": false,
     "score": 0.5392,
     "latencyMs": 2271.8665249994956,
     "error": null
    },
    {
     "taskId": "p030-record-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1420.1724440063117,
     "error": null
    },
    {
     "taskId": "p031-article-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1292.8679210017435,
     "error": null
    },
    {
     "taskId": "p032-table-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1341.3301599939587,
     "error": null
    },
    {
     "taskId": "p033-docs-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1415.3395519970218,
     "error": null
    },
    {
     "taskId": "p034-pricing-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1302.4275550051243,
     "error": null
    },
    {
     "taskId": "p035-news-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1310.9663940049359,
     "error": null
    },
    {
     "taskId": "p036-record-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1364.6047310030553,
     "error": null
    },
    {
     "taskId": "p037-article-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1353.800910001155,
     "error": null
    },
    {
     "taskId": "p038-table-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1331.2452780010062,
     "error": null
    },
    {
     "taskId": "p039-docs-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1320.6201889988733,
     "error": null
    },
    {
     "taskId": "p040-pricing-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1971.3838560055592,
     "error": null
    },
    {
     "taskId": "p041-news-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1639.989268995123,
     "error": null
    },
    {
     "taskId": "p042-record-soft_paywall",
     "passed": true,
     "score": 0.9427,
     "latencyMs": 1696.9528829940828,
     "error": null
    },
    {
     "taskId": "p043-article-soft_paywall",
     "passed": true,
     "score": 0.9714,
     "latencyMs": 1668.1687820018851,
     "error": null
    },
    {
     "taskId": "p044-table-soft_paywall",
     "passed": true,
     "score": 0.9935,
     "latencyMs": 1626.8219980047434,
     "error": null
    },
    {
     "taskId": "p045-docs-soft_paywall",
     "passed": true,
     "score": 0.9452,
     "latencyMs": 1658.098603002145,
     "error": null
    },
    {
     "taskId": "p046-pricing-soft_paywall",
     "passed": true,
     "score": 0.9526,
     "latencyMs": 1720.5312790028984,
     "error": null
    },
    {
     "taskId": "p047-news-soft_paywall",
     "passed": true,
     "score": 0.9627,
     "latencyMs": 1610.9820310011855,
     "error": null
    },
    {
     "taskId": "p048-record-clean",
     "passed": true,
     "score": 0.9816,
     "latencyMs": 1680.2374139952008,
     "error": null
    },
    {
     "taskId": "p049-article-clean",
     "passed": true,
     "score": 0.9727,
     "latencyMs": 1704.9125889971037,
     "error": null
    },
    {
     "taskId": "p050-table-clean",
     "passed": true,
     "score": 0.9926,
     "latencyMs": 892.6076370044029,
     "error": null
    },
    {
     "taskId": "p051-docs-clean",
     "passed": true,
     "score": 0.9461,
     "latencyMs": 839.009936004004,
     "error": null
    },
    {
     "taskId": "p052-pricing-clean",
     "passed": true,
     "score": 0.9543,
     "latencyMs": 810.0848380054231,
     "error": null
    },
    {
     "taskId": "p053-news-clean",
     "passed": true,
     "score": 0.953,
     "latencyMs": 906.0535649987287,
     "error": null
    },
    {
     "taskId": "p054-record-heavy_chrome",
     "passed": true,
     "score": 0.9551,
     "latencyMs": 908.7479390000226,
     "error": null
    },
    {
     "taskId": "p055-article-heavy_chrome",
     "passed": true,
     "score": 0.9722,
     "latencyMs": 933.7359089986421,
     "error": null
    },
    {
     "taskId": "p056-table-heavy_chrome",
     "passed": true,
     "score": 0.9447,
     "latencyMs": 856.9062780006789,
     "error": null
    },
    {
     "taskId": "p057-docs-heavy_chrome",
     "passed": true,
     "score": 0.9447,
     "latencyMs": 739.0991259962902,
     "error": null
    },
    {
     "taskId": "p058-pricing-heavy_chrome",
     "passed": true,
     "score": 0.9523,
     "latencyMs": 788.0140439956449,
     "error": null
    },
    {
     "taskId": "p059-news-heavy_chrome",
     "passed": true,
     "score": 0.9665,
     "latencyMs": 659.4744739995804,
     "error": null
    },
    {
     "taskId": "p060-record-consent_overlay",
     "passed": true,
     "score": 0.9731,
     "latencyMs": 4043.5097189983935,
     "error": null
    },
    {
     "taskId": "p061-article-consent_overlay",
     "passed": true,
     "score": 0.9689,
     "latencyMs": 4043.768158997409,
     "error": null
    },
    {
     "taskId": "p062-table-consent_overlay",
     "passed": false,
     "score": 0.0,
     "latencyMs": 4043.1611519961734,
     "error": null
    },
    {
     "taskId": "p063-docs-consent_overlay",
     "passed": true,
     "score": 0.9441,
     "latencyMs": 4384.304790997703,
     "error": null
    },
    {
     "taskId": "p064-pricing-consent_overlay",
     "passed": true,
     "score": 0.9507,
     "latencyMs": 4043.972906001727,
     "error": null
    },
    {
     "taskId": "p065-news-consent_overlay",
     "passed": true,
     "score": 0.9693,
     "latencyMs": 4042.6868249996915,
     "error": null
    },
    {
     "taskId": "p066-record-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 4041.5455659967847,
     "error": null
    },
    {
     "taskId": "p067-article-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 4383.583896997152,
     "error": null
    },
    {
     "taskId": "p068-table-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 4383.924221001507,
     "error": null
    },
    {
     "taskId": "p069-docs-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 4042.0897509975475,
     "error": null
    },
    {
     "taskId": "p070-pricing-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1944.9844249975285,
     "error": null
    },
    {
     "taskId": "p071-news-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1759.4214150012704,
     "error": null
    },
    {
     "taskId": "p072-record-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1913.0854780014488,
     "error": null
    },
    {
     "taskId": "p073-article-lazy",
     "passed": false,
     "score": 0.6381,
     "latencyMs": 1924.8838950006757,
     "error": null
    },
    {
     "taskId": "p074-table-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1860.713191999821,
     "error": null
    },
    {
     "taskId": "p075-docs-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1824.6171499995398,
     "error": null
    },
    {
     "taskId": "p076-pricing-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1892.6418150003883,
     "error": null
    },
    {
     "taskId": "p077-news-lazy",
     "passed": false,
     "score": 0.544,
     "latencyMs": 1871.7723259978811,
     "error": null
    },
    {
     "taskId": "p078-record-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1840.1771649951115,
     "error": null
    },
    {
     "taskId": "p079-article-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1959.841048999806,
     "error": null
    },
    {
     "taskId": "p080-table-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 3515.2556570028537,
     "error": null
    },
    {
     "taskId": "p081-docs-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 3197.1064239987754,
     "error": null
    },
    {
     "taskId": "p082-pricing-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 3522.9116979971877,
     "error": null
    },
    {
     "taskId": "p083-news-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 3197.4241950010764,
     "error": null
    },
    {
     "taskId": "p084-record-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 3578.4897250050562,
     "error": null
    },
    {
     "taskId": "p085-article-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 3560.1531360007357,
     "error": null
    },
    {
     "taskId": "p086-table-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 3550.018032998196,
     "error": null
    },
    {
     "taskId": "p087-docs-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 3531.19003699976,
     "error": null
    },
    {
     "taskId": "p088-pricing-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 3540.1552569965133,
     "error": null
    },
    {
     "taskId": "p089-news-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 3569.6309380000457,
     "error": null
    },
    {
     "taskId": "p090-record-soft_paywall",
     "passed": true,
     "score": 0.9411,
     "latencyMs": 905.3766010038089,
     "error": null
    },
    {
     "taskId": "p091-article-soft_paywall",
     "passed": true,
     "score": 0.9685,
     "latencyMs": 1002.5779799980228,
     "error": null
    },
    {
     "taskId": "p092-table-soft_paywall",
     "passed": true,
     "score": 0.9506,
     "latencyMs": 1005.4224179984885,
     "error": null
    },
    {
     "taskId": "p093-docs-soft_paywall",
     "passed": true,
     "score": 0.948,
     "latencyMs": 993.7674090033397,
     "error": null
    },
    {
     "taskId": "p094-pricing-soft_paywall",
     "passed": true,
     "score": 0.9512,
     "latencyMs": 973.1860350002535,
     "error": null
    },
    {
     "taskId": "p095-news-soft_paywall",
     "passed": true,
     "score": 0.9624,
     "latencyMs": 910.677971005498,
     "error": null
    }
   ]
  },
  {
   "benchmarkId": "webbench-fetch",
   "suite": "fetch",
   "runId": "webbench-fetch-browserbase-20260919-r4",
   "startedAt": "2026-09-19T08:52:08Z",
   "finishedAt": "2026-09-19T09:05:06Z",
   "vendor": {
    "name": "Browserbase",
    "product": "Fetch API",
    "endpoint": "https://api.browserbase.com/v1/fetch",
    "configuration": "format markdown, no proxies, no redirects"
   },
   "harness": "webbench.fetch_bench (hosted protocol, public tunnel)",
   "selection": "All 96 generated pages (record, article and table pages through five chrome profiles), one request per page, no retries, same sitting as every other fetcher in this section.",
   "disclosure": "Pages are generated from a WebBench world and served through a throw-away public tunnel; the generator knows every content unit it emitted. Pass = usable page: content recall ≥ 0.9 and signal ratio ≥ 0.3 (TinyFish's own usability floor). Score = content F1, the harmonic mean of content recall and signal ratio, so neither a clean stub nor a full-page dump scores well. A provider error counts as 0. No LLM judge. Profiles: clean, heavy chrome, consent overlay, client-side rendered, late content.",
   "metric": {
    "label": "Content F1",
    "higherIsBetter": true
   },
   "aggregate": {
    "tasks": 96,
    "attempted": 96,
    "graded": 96,
    "passed": 21,
    "errors": 0,
    "meanScore": 0.1873,
    "latencyMsP50": 627.3,
    "costUsdTotal": null
   },
   "reference": [
    {
     "name": "Chromium, rendered <main> text 2 s after load (reference ceiling, not ranked)",
     "passed": 96,
     "meanScore": 1.0
    },
    {
     "name": "raw HTML with tags stripped, no rendering (floor, not ranked)",
     "passed": 36,
     "meanScore": 0.5187
    }
   ],
   "trials": [
    {
     "taskId": "p000-record-clean",
     "passed": false,
     "score": 0.3889,
     "latencyMs": 744.7,
     "error": null
    },
    {
     "taskId": "p001-article-clean",
     "passed": true,
     "score": 0.6195,
     "latencyMs": 823.2,
     "error": null
    },
    {
     "taskId": "p002-table-clean",
     "passed": true,
     "score": 0.553,
     "latencyMs": 637.8,
     "error": null
    },
    {
     "taskId": "p003-docs-clean",
     "passed": true,
     "score": 0.5861,
     "latencyMs": 619.6,
     "error": null
    },
    {
     "taskId": "p004-pricing-clean",
     "passed": false,
     "score": 0.0743,
     "latencyMs": 615.0,
     "error": null
    },
    {
     "taskId": "p005-news-clean",
     "passed": true,
     "score": 0.5499,
     "latencyMs": 626.1,
     "error": null
    },
    {
     "taskId": "p006-record-heavy_chrome",
     "passed": false,
     "score": 0.076,
     "latencyMs": 697.2,
     "error": null
    },
    {
     "taskId": "p007-article-heavy_chrome",
     "passed": false,
     "score": 0.127,
     "latencyMs": 819.6,
     "error": null
    },
    {
     "taskId": "p008-table-heavy_chrome",
     "passed": false,
     "score": 0.0665,
     "latencyMs": 677.2,
     "error": null
    },
    {
     "taskId": "p009-docs-heavy_chrome",
     "passed": false,
     "score": 0.0736,
     "latencyMs": 628.9,
     "error": null
    },
    {
     "taskId": "p010-pricing-heavy_chrome",
     "passed": false,
     "score": 0.0113,
     "latencyMs": 697.2,
     "error": null
    },
    {
     "taskId": "p011-news-heavy_chrome",
     "passed": false,
     "score": 0.0778,
     "latencyMs": 658.1,
     "error": null
    },
    {
     "taskId": "p012-record-consent_overlay",
     "passed": false,
     "score": 0.2996,
     "latencyMs": 596.7,
     "error": null
    },
    {
     "taskId": "p013-article-consent_overlay",
     "passed": true,
     "score": 0.543,
     "latencyMs": 581.2,
     "error": null
    },
    {
     "taskId": "p014-table-consent_overlay",
     "passed": false,
     "score": 0.4071,
     "latencyMs": 576.1,
     "error": null
    },
    {
     "taskId": "p015-docs-consent_overlay",
     "passed": false,
     "score": 0.4172,
     "latencyMs": 593.9,
     "error": null
    },
    {
     "taskId": "p016-pricing-consent_overlay",
     "passed": false,
     "score": 0.0898,
     "latencyMs": 614.8,
     "error": null
    },
    {
     "taskId": "p017-news-consent_overlay",
     "passed": true,
     "score": 0.4897,
     "latencyMs": 743.7,
     "error": null
    },
    {
     "taskId": "p018-record-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 634.9,
     "error": null
    },
    {
     "taskId": "p019-article-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 604.7,
     "error": null
    },
    {
     "taskId": "p020-table-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 575.9,
     "error": null
    },
    {
     "taskId": "p021-docs-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 593.3,
     "error": null
    },
    {
     "taskId": "p022-pricing-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 615.6,
     "error": null
    },
    {
     "taskId": "p023-news-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 617.3,
     "error": null
    },
    {
     "taskId": "p024-record-lazy",
     "passed": false,
     "score": 0.0142,
     "latencyMs": 627.3,
     "error": null
    },
    {
     "taskId": "p025-article-lazy",
     "passed": false,
     "score": 0.3563,
     "latencyMs": 629.8,
     "error": null
    },
    {
     "taskId": "p026-table-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 613.1,
     "error": null
    },
    {
     "taskId": "p027-docs-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 730.7,
     "error": null
    },
    {
     "taskId": "p028-pricing-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 595.0,
     "error": null
    },
    {
     "taskId": "p029-news-lazy",
     "passed": false,
     "score": 0.2693,
     "latencyMs": 605.8,
     "error": null
    },
    {
     "taskId": "p030-record-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 580.6,
     "error": null
    },
    {
     "taskId": "p031-article-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 593.1,
     "error": null
    },
    {
     "taskId": "p032-table-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 651.2,
     "error": null
    },
    {
     "taskId": "p033-docs-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 602.8,
     "error": null
    },
    {
     "taskId": "p034-pricing-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 594.4,
     "error": null
    },
    {
     "taskId": "p035-news-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 575.3,
     "error": null
    },
    {
     "taskId": "p036-record-shadow_dom",
     "passed": false,
     "score": 0.0147,
     "latencyMs": 598.3,
     "error": null
    },
    {
     "taskId": "p037-article-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 621.5,
     "error": null
    },
    {
     "taskId": "p038-table-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 580.5,
     "error": null
    },
    {
     "taskId": "p039-docs-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 647.7,
     "error": null
    },
    {
     "taskId": "p040-pricing-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 613.7,
     "error": null
    },
    {
     "taskId": "p041-news-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 601.9,
     "error": null
    },
    {
     "taskId": "p042-record-soft_paywall",
     "passed": false,
     "score": 0.3691,
     "latencyMs": 575.4,
     "error": null
    },
    {
     "taskId": "p043-article-soft_paywall",
     "passed": true,
     "score": 0.6236,
     "latencyMs": 635.0,
     "error": null
    },
    {
     "taskId": "p044-table-soft_paywall",
     "passed": true,
     "score": 0.5959,
     "latencyMs": 584.7,
     "error": null
    },
    {
     "taskId": "p045-docs-soft_paywall",
     "passed": true,
     "score": 0.5087,
     "latencyMs": 678.0,
     "error": null
    },
    {
     "taskId": "p046-pricing-soft_paywall",
     "passed": false,
     "score": 0.0875,
     "latencyMs": 583.0,
     "error": null
    },
    {
     "taskId": "p047-news-soft_paywall",
     "passed": true,
     "score": 0.5724,
     "latencyMs": 590.3,
     "error": null
    },
    {
     "taskId": "p048-record-clean",
     "passed": true,
     "score": 0.5699,
     "latencyMs": 622.1,
     "error": null
    },
    {
     "taskId": "p049-article-clean",
     "passed": true,
     "score": 0.6487,
     "latencyMs": 596.1,
     "error": null
    },
    {
     "taskId": "p050-table-clean",
     "passed": true,
     "score": 0.5781,
     "latencyMs": 608.9,
     "error": null
    },
    {
     "taskId": "p051-docs-clean",
     "passed": true,
     "score": 0.5075,
     "latencyMs": 614.8,
     "error": null
    },
    {
     "taskId": "p052-pricing-clean",
     "passed": false,
     "score": 0.0906,
     "latencyMs": 605.7,
     "error": null
    },
    {
     "taskId": "p053-news-clean",
     "passed": true,
     "score": 0.5279,
     "latencyMs": 619.4,
     "error": null
    },
    {
     "taskId": "p054-record-heavy_chrome",
     "passed": false,
     "score": 0.0552,
     "latencyMs": 640.6,
     "error": null
    },
    {
     "taskId": "p055-article-heavy_chrome",
     "passed": false,
     "score": 0.1123,
     "latencyMs": 666.7,
     "error": null
    },
    {
     "taskId": "p056-table-heavy_chrome",
     "passed": false,
     "score": 0.0861,
     "latencyMs": 700.0,
     "error": null
    },
    {
     "taskId": "p057-docs-heavy_chrome",
     "passed": false,
     "score": 0.0712,
     "latencyMs": 690.1,
     "error": null
    },
    {
     "taskId": "p058-pricing-heavy_chrome",
     "passed": false,
     "score": 0.0117,
     "latencyMs": 704.6,
     "error": null
    },
    {
     "taskId": "p059-news-heavy_chrome",
     "passed": false,
     "score": 0.1335,
     "latencyMs": 754.3,
     "error": null
    },
    {
     "taskId": "p060-record-consent_overlay",
     "passed": false,
     "score": 0.416,
     "latencyMs": 608.6,
     "error": null
    },
    {
     "taskId": "p061-article-consent_overlay",
     "passed": true,
     "score": 0.5426,
     "latencyMs": 594.2,
     "error": null
    },
    {
     "taskId": "p062-table-consent_overlay",
     "passed": false,
     "score": 0.3516,
     "latencyMs": 650.7,
     "error": null
    },
    {
     "taskId": "p063-docs-consent_overlay",
     "passed": false,
     "score": 0.4431,
     "latencyMs": 624.5,
     "error": null
    },
    {
     "taskId": "p064-pricing-consent_overlay",
     "passed": false,
     "score": 0.0773,
     "latencyMs": 593.2,
     "error": null
    },
    {
     "taskId": "p065-news-consent_overlay",
     "passed": true,
     "score": 0.5634,
     "latencyMs": 632.5,
     "error": null
    },
    {
     "taskId": "p066-record-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 652.1,
     "error": null
    },
    {
     "taskId": "p067-article-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 665.3,
     "error": null
    },
    {
     "taskId": "p068-table-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 628.9,
     "error": null
    },
    {
     "taskId": "p069-docs-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 635.4,
     "error": null
    },
    {
     "taskId": "p070-pricing-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 608.3,
     "error": null
    },
    {
     "taskId": "p071-news-csr",
     "passed": false,
     "score": 0.0,
     "latencyMs": 627.0,
     "error": null
    },
    {
     "taskId": "p072-record-lazy",
     "passed": false,
     "score": 0.0142,
     "latencyMs": 669.9,
     "error": null
    },
    {
     "taskId": "p073-article-lazy",
     "passed": false,
     "score": 0.3487,
     "latencyMs": 658.2,
     "error": null
    },
    {
     "taskId": "p074-table-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 617.1,
     "error": null
    },
    {
     "taskId": "p075-docs-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 642.5,
     "error": null
    },
    {
     "taskId": "p076-pricing-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 643.7,
     "error": null
    },
    {
     "taskId": "p077-news-lazy",
     "passed": false,
     "score": 0.2932,
     "latencyMs": 620.2,
     "error": null
    },
    {
     "taskId": "p078-record-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 656.4,
     "error": null
    },
    {
     "taskId": "p079-article-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 658.6,
     "error": null
    },
    {
     "taskId": "p080-table-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 644.0,
     "error": null
    },
    {
     "taskId": "p081-docs-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 647.7,
     "error": null
    },
    {
     "taskId": "p082-pricing-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 650.7,
     "error": null
    },
    {
     "taskId": "p083-news-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 623.0,
     "error": null
    },
    {
     "taskId": "p084-record-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 632.8,
     "error": null
    },
    {
     "taskId": "p085-article-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 641.1,
     "error": null
    },
    {
     "taskId": "p086-table-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 624.2,
     "error": null
    },
    {
     "taskId": "p087-docs-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 643.1,
     "error": null
    },
    {
     "taskId": "p088-pricing-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 648.3,
     "error": null
    },
    {
     "taskId": "p089-news-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 650.5,
     "error": null
    },
    {
     "taskId": "p090-record-soft_paywall",
     "passed": false,
     "score": 0.3621,
     "latencyMs": 653.5,
     "error": null
    },
    {
     "taskId": "p091-article-soft_paywall",
     "passed": true,
     "score": 0.5997,
     "latencyMs": 630.5,
     "error": null
    },
    {
     "taskId": "p092-table-soft_paywall",
     "passed": true,
     "score": 0.5451,
     "latencyMs": 636.1,
     "error": null
    },
    {
     "taskId": "p093-docs-soft_paywall",
     "passed": true,
     "score": 0.4987,
     "latencyMs": 707.9,
     "error": null
    },
    {
     "taskId": "p094-pricing-soft_paywall",
     "passed": false,
     "score": 0.0951,
     "latencyMs": 627.3,
     "error": null
    },
    {
     "taskId": "p095-news-soft_paywall",
     "passed": true,
     "score": 0.5712,
     "latencyMs": 627.4,
     "error": null
    }
   ]
  },
  {
   "benchmarkId": "webbench-fetch",
   "suite": "fetch",
   "runId": "webbench-fetch-jina-20260919-r4",
   "startedAt": "2026-09-19T08:52:08Z",
   "finishedAt": "2026-09-19T09:05:06Z",
   "vendor": {
    "name": "Jina AI",
    "product": "Reader",
    "endpoint": "https://r.jina.ai/<url>",
    "configuration": "keyless tier, X-No-Cache, text output"
   },
   "harness": "webbench.fetch_bench (hosted protocol, public tunnel)",
   "selection": "All 96 generated pages (record, article and table pages through five chrome profiles), one request per page, no retries, same sitting as every other fetcher in this section.",
   "disclosure": "Pages are generated from a WebBench world and served through a throw-away public tunnel; the generator knows every content unit it emitted. Pass = usable page: content recall ≥ 0.9 and signal ratio ≥ 0.3 (TinyFish's own usability floor). Score = content F1, the harmonic mean of content recall and signal ratio, so neither a clean stub nor a full-page dump scores well. A provider error counts as 0. No LLM judge. Profiles: clean, heavy chrome, consent overlay, client-side rendered, late content.",
   "metric": {
    "label": "Content F1",
    "higherIsBetter": true
   },
   "aggregate": {
    "tasks": 96,
    "attempted": 96,
    "graded": 96,
    "passed": 41,
    "errors": 0,
    "meanScore": 0.4283,
    "latencyMsP50": 1125.0,
    "costUsdTotal": null
   },
   "reference": [
    {
     "name": "Chromium, rendered <main> text 2 s after load (reference ceiling, not ranked)",
     "passed": 96,
     "meanScore": 1.0
    },
    {
     "name": "raw HTML with tags stripped, no rendering (floor, not ranked)",
     "passed": 36,
     "meanScore": 0.5187
    }
   ],
   "trials": [
    {
     "taskId": "p000-record-clean",
     "passed": true,
     "score": 0.8376,
     "latencyMs": 1992.3,
     "error": null
    },
    {
     "taskId": "p001-article-clean",
     "passed": true,
     "score": 0.9225,
     "latencyMs": 1593.3,
     "error": null
    },
    {
     "taskId": "p002-table-clean",
     "passed": true,
     "score": 0.5195,
     "latencyMs": 1009.0,
     "error": null
    },
    {
     "taskId": "p003-docs-clean",
     "passed": true,
     "score": 0.9064,
     "latencyMs": 1176.7,
     "error": null
    },
    {
     "taskId": "p004-pricing-clean",
     "passed": true,
     "score": 0.7969,
     "latencyMs": 1183.9,
     "error": null
    },
    {
     "taskId": "p005-news-clean",
     "passed": true,
     "score": 0.9,
     "latencyMs": 1034.4,
     "error": null
    },
    {
     "taskId": "p006-record-heavy_chrome",
     "passed": false,
     "score": 0.0767,
     "latencyMs": 1276.2,
     "error": null
    },
    {
     "taskId": "p007-article-heavy_chrome",
     "passed": false,
     "score": 0.1279,
     "latencyMs": 1270.3,
     "error": null
    },
    {
     "taskId": "p008-table-heavy_chrome",
     "passed": false,
     "score": 0.1442,
     "latencyMs": 1214.9,
     "error": null
    },
    {
     "taskId": "p009-docs-heavy_chrome",
     "passed": false,
     "score": 0.0743,
     "latencyMs": 1051.0,
     "error": null
    },
    {
     "taskId": "p010-pricing-heavy_chrome",
     "passed": false,
     "score": 0.0361,
     "latencyMs": 1212.3,
     "error": null
    },
    {
     "taskId": "p011-news-heavy_chrome",
     "passed": false,
     "score": 0.0784,
     "latencyMs": 1053.1,
     "error": null
    },
    {
     "taskId": "p012-record-consent_overlay",
     "passed": true,
     "score": 0.8173,
     "latencyMs": 1131.6,
     "error": null
    },
    {
     "taskId": "p013-article-consent_overlay",
     "passed": true,
     "score": 0.9182,
     "latencyMs": 1342.7,
     "error": null
    },
    {
     "taskId": "p014-table-consent_overlay",
     "passed": false,
     "score": 0.4502,
     "latencyMs": 1234.6,
     "error": null
    },
    {
     "taskId": "p015-docs-consent_overlay",
     "passed": true,
     "score": 0.8681,
     "latencyMs": 1025.8,
     "error": null
    },
    {
     "taskId": "p016-pricing-consent_overlay",
     "passed": true,
     "score": 0.8208,
     "latencyMs": 1177.3,
     "error": null
    },
    {
     "taskId": "p017-news-consent_overlay",
     "passed": true,
     "score": 0.9011,
     "latencyMs": 1623.4,
     "error": null
    },
    {
     "taskId": "p018-record-csr",
     "passed": true,
     "score": 0.804,
     "latencyMs": 1200.7,
     "error": null
    },
    {
     "taskId": "p019-article-csr",
     "passed": true,
     "score": 0.937,
     "latencyMs": 1203.7,
     "error": null
    },
    {
     "taskId": "p020-table-csr",
     "passed": false,
     "score": 0.4505,
     "latencyMs": 1009.2,
     "error": null
    },
    {
     "taskId": "p021-docs-csr",
     "passed": true,
     "score": 0.8883,
     "latencyMs": 1313.7,
     "error": null
    },
    {
     "taskId": "p022-pricing-csr",
     "passed": true,
     "score": 0.8069,
     "latencyMs": 1081.0,
     "error": null
    },
    {
     "taskId": "p023-news-csr",
     "passed": true,
     "score": 0.9301,
     "latencyMs": 2845.7,
     "error": null
    },
    {
     "taskId": "p024-record-lazy",
     "passed": false,
     "score": 0.0132,
     "latencyMs": 1020.9,
     "error": null
    },
    {
     "taskId": "p025-article-lazy",
     "passed": false,
     "score": 0.5969,
     "latencyMs": 1007.3,
     "error": null
    },
    {
     "taskId": "p026-table-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1024.2,
     "error": null
    },
    {
     "taskId": "p027-docs-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1040.1,
     "error": null
    },
    {
     "taskId": "p028-pricing-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1039.0,
     "error": null
    },
    {
     "taskId": "p029-news-lazy",
     "passed": false,
     "score": 0.4868,
     "latencyMs": 1011.9,
     "error": null
    },
    {
     "taskId": "p030-record-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1139.0,
     "error": null
    },
    {
     "taskId": "p031-article-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1601.0,
     "error": null
    },
    {
     "taskId": "p032-table-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 2733.8,
     "error": null
    },
    {
     "taskId": "p033-docs-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1439.2,
     "error": null
    },
    {
     "taskId": "p034-pricing-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1211.7,
     "error": null
    },
    {
     "taskId": "p035-news-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1703.1,
     "error": null
    },
    {
     "taskId": "p036-record-shadow_dom",
     "passed": false,
     "score": 0.0382,
     "latencyMs": 948.0,
     "error": null
    },
    {
     "taskId": "p037-article-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1102.6,
     "error": null
    },
    {
     "taskId": "p038-table-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1424.0,
     "error": null
    },
    {
     "taskId": "p039-docs-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1140.8,
     "error": null
    },
    {
     "taskId": "p040-pricing-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1180.2,
     "error": null
    },
    {
     "taskId": "p041-news-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1000.6,
     "error": null
    },
    {
     "taskId": "p042-record-soft_paywall",
     "passed": false,
     "score": 0.3444,
     "latencyMs": 1002.6,
     "error": null
    },
    {
     "taskId": "p043-article-soft_paywall",
     "passed": true,
     "score": 0.9256,
     "latencyMs": 1074.7,
     "error": null
    },
    {
     "taskId": "p044-table-soft_paywall",
     "passed": true,
     "score": 0.5604,
     "latencyMs": 1539.0,
     "error": null
    },
    {
     "taskId": "p045-docs-soft_paywall",
     "passed": true,
     "score": 0.8794,
     "latencyMs": 1255.5,
     "error": null
    },
    {
     "taskId": "p046-pricing-soft_paywall",
     "passed": false,
     "score": 0.3034,
     "latencyMs": 1087.5,
     "error": null
    },
    {
     "taskId": "p047-news-soft_paywall",
     "passed": true,
     "score": 0.91,
     "latencyMs": 2587.3,
     "error": null
    },
    {
     "taskId": "p048-record-clean",
     "passed": true,
     "score": 0.9228,
     "latencyMs": 1039.3,
     "error": null
    },
    {
     "taskId": "p049-article-clean",
     "passed": true,
     "score": 0.9311,
     "latencyMs": 1278.3,
     "error": null
    },
    {
     "taskId": "p050-table-clean",
     "passed": true,
     "score": 0.9242,
     "latencyMs": 1000.7,
     "error": null
    },
    {
     "taskId": "p051-docs-clean",
     "passed": true,
     "score": 0.8794,
     "latencyMs": 1006.4,
     "error": null
    },
    {
     "taskId": "p052-pricing-clean",
     "passed": true,
     "score": 0.8255,
     "latencyMs": 2836.4,
     "error": null
    },
    {
     "taskId": "p053-news-clean",
     "passed": true,
     "score": 0.8917,
     "latencyMs": 1062.2,
     "error": null
    },
    {
     "taskId": "p054-record-heavy_chrome",
     "passed": false,
     "score": 0.0558,
     "latencyMs": 1106.5,
     "error": null
    },
    {
     "taskId": "p055-article-heavy_chrome",
     "passed": false,
     "score": 0.1132,
     "latencyMs": 1167.8,
     "error": null
    },
    {
     "taskId": "p056-table-heavy_chrome",
     "passed": false,
     "score": 0.0867,
     "latencyMs": 1126.9,
     "error": null
    },
    {
     "taskId": "p057-docs-heavy_chrome",
     "passed": false,
     "score": 0.0717,
     "latencyMs": 1200.8,
     "error": null
    },
    {
     "taskId": "p058-pricing-heavy_chrome",
     "passed": false,
     "score": 0.0338,
     "latencyMs": 1964.4,
     "error": null
    },
    {
     "taskId": "p059-news-heavy_chrome",
     "passed": false,
     "score": 0.1343,
     "latencyMs": 1033.9,
     "error": null
    },
    {
     "taskId": "p060-record-consent_overlay",
     "passed": true,
     "score": 0.891,
     "latencyMs": 1105.8,
     "error": null
    },
    {
     "taskId": "p061-article-consent_overlay",
     "passed": true,
     "score": 0.9181,
     "latencyMs": 1049.2,
     "error": null
    },
    {
     "taskId": "p062-table-consent_overlay",
     "passed": false,
     "score": 0.3924,
     "latencyMs": 1164.4,
     "error": null
    },
    {
     "taskId": "p063-docs-consent_overlay",
     "passed": true,
     "score": 0.8758,
     "latencyMs": 1027.8,
     "error": null
    },
    {
     "taskId": "p064-pricing-consent_overlay",
     "passed": true,
     "score": 0.8042,
     "latencyMs": 1029.0,
     "error": null
    },
    {
     "taskId": "p065-news-consent_overlay",
     "passed": true,
     "score": 0.9243,
     "latencyMs": 1079.7,
     "error": null
    },
    {
     "taskId": "p066-record-csr",
     "passed": true,
     "score": 0.8773,
     "latencyMs": 1124.0,
     "error": null
    },
    {
     "taskId": "p067-article-csr",
     "passed": true,
     "score": 0.924,
     "latencyMs": 1282.8,
     "error": null
    },
    {
     "taskId": "p068-table-csr",
     "passed": true,
     "score": 0.9557,
     "latencyMs": 1039.8,
     "error": null
    },
    {
     "taskId": "p069-docs-csr",
     "passed": true,
     "score": 0.8872,
     "latencyMs": 1015.7,
     "error": null
    },
    {
     "taskId": "p070-pricing-csr",
     "passed": true,
     "score": 0.8383,
     "latencyMs": 1027.1,
     "error": null
    },
    {
     "taskId": "p071-news-csr",
     "passed": true,
     "score": 0.9355,
     "latencyMs": 1192.6,
     "error": null
    },
    {
     "taskId": "p072-record-lazy",
     "passed": false,
     "score": 0.0132,
     "latencyMs": 959.9,
     "error": null
    },
    {
     "taskId": "p073-article-lazy",
     "passed": false,
     "score": 0.5943,
     "latencyMs": 1890.1,
     "error": null
    },
    {
     "taskId": "p074-table-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1102.5,
     "error": null
    },
    {
     "taskId": "p075-docs-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1169.3,
     "error": null
    },
    {
     "taskId": "p076-pricing-lazy",
     "passed": false,
     "score": 0.0,
     "latencyMs": 7936.4,
     "error": null
    },
    {
     "taskId": "p077-news-lazy",
     "passed": false,
     "score": 0.4979,
     "latencyMs": 990.4,
     "error": null
    },
    {
     "taskId": "p078-record-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1735.8,
     "error": null
    },
    {
     "taskId": "p079-article-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1073.7,
     "error": null
    },
    {
     "taskId": "p080-table-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1441.6,
     "error": null
    },
    {
     "taskId": "p081-docs-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1125.9,
     "error": null
    },
    {
     "taskId": "p082-pricing-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1363.2,
     "error": null
    },
    {
     "taskId": "p083-news-iframe_embed",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1242.0,
     "error": null
    },
    {
     "taskId": "p084-record-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1000.6,
     "error": null
    },
    {
     "taskId": "p085-article-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1044.8,
     "error": null
    },
    {
     "taskId": "p086-table-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1096.6,
     "error": null
    },
    {
     "taskId": "p087-docs-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1098.7,
     "error": null
    },
    {
     "taskId": "p088-pricing-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 963.7,
     "error": null
    },
    {
     "taskId": "p089-news-shadow_dom",
     "passed": false,
     "score": 0.0,
     "latencyMs": 1114.1,
     "error": null
    },
    {
     "taskId": "p090-record-soft_paywall",
     "passed": false,
     "score": 0.3376,
     "latencyMs": 1432.2,
     "error": null
    },
    {
     "taskId": "p091-article-soft_paywall",
     "passed": true,
     "score": 0.9183,
     "latencyMs": 1371.4,
     "error": null
    },
    {
     "taskId": "p092-table-soft_paywall",
     "passed": true,
     "score": 0.5094,
     "latencyMs": 1096.7,
     "error": null
    },
    {
     "taskId": "p093-docs-soft_paywall",
     "passed": true,
     "score": 0.8789,
     "latencyMs": 1101.5,
     "error": null
    },
    {
     "taskId": "p094-pricing-soft_paywall",
     "passed": false,
     "score": 0.2969,
     "latencyMs": 1091.8,
     "error": null
    },
    {
     "taskId": "p095-news-soft_paywall",
     "passed": true,
     "score": 0.9095,
     "latencyMs": 994.5,
     "error": null
    }
   ]
  },
  {
   "benchmarkId": "webbench-search",
   "suite": "search",
   "runId": "webbench-search-tinyfish-20260919-r3",
   "startedAt": "2026-09-19T06:51:55Z",
   "finishedAt": "2026-09-19T06:55:37Z",
   "vendor": {
    "name": "TinyFish",
    "product": "Search API",
    "endpoint": "https://api.search.tinyfish.ai",
    "configuration": "query only, documented defaults"
   },
   "harness": "webbench.search_bench (live index)",
   "selection": "60 arXiv papers in three age buckets (submitted 2–4 days, ≈ 30 days and ≈ 365 days before the run), queried by title; one request per item, no retries; every provider saw the same items.",
   "disclosure": "Live-web suite by necessity (a search index covers the public web). Items are drawn from arXiv's API on the run date, so the set is new each run. Pass = the paper's arXiv identifier appears in the rank-1 result URL; score = reciprocal rank within the top 10. No LLM judge.",
   "metric": {
    "label": "MRR",
    "higherIsBetter": true
   },
   "aggregate": {
    "tasks": 60,
    "attempted": 60,
    "graded": 60,
    "passed": 23,
    "errors": 0,
    "meanScore": 0.3889,
    "latencyMsP50": 139.3,
    "costUsdTotal": 0.0
   },
   "reference": [],
   "trials": [
    {
     "taskId": "fresh:2609.20812",
     "passed": false,
     "score": 0.0,
     "latencyMs": 138.0,
     "error": null
    },
    {
     "taskId": "fresh:2609.20815",
     "passed": false,
     "score": 0.0,
     "latencyMs": 107.2,
     "error": null
    },
    {
     "taskId": "fresh:2609.20816",
     "passed": false,
     "score": 0.0,
     "latencyMs": 150.5,
     "error": null
    },
    {
     "taskId": "fresh:2609.20817",
     "passed": false,
     "score": 0.0,
     "latencyMs": 253.5,
     "error": null
    },
    {
     "taskId": "fresh:2609.20820",
     "passed": false,
     "score": 0.0,
     "latencyMs": 108.4,
     "error": null
    },
    {
     "taskId": "fresh:2609.20822",
     "passed": false,
     "score": 0.0,
     "latencyMs": 246.3,
     "error": null
    },
    {
     "taskId": "fresh:2609.20784",
     "passed": false,
     "score": 0.0,
     "latencyMs": 131.2,
     "error": null
    },
    {
     "taskId": "fresh:2609.20800",
     "passed": true,
     "score": 1.0,
     "latencyMs": 147.2,
     "error": null
    },
    {
     "taskId": "fresh:2609.20804",
     "passed": false,
     "score": 0.0,
     "latencyMs": 116.7,
     "error": null
    },
    {
     "taskId": "fresh:2609.20808",
     "passed": false,
     "score": 0.0,
     "latencyMs": 230.8,
     "error": null
    },
    {
     "taskId": "fresh:2609.20821",
     "passed": false,
     "score": 0.0,
     "latencyMs": 248.2,
     "error": null
    },
    {
     "taskId": "fresh:2609.19831",
     "passed": false,
     "score": 0.0,
     "latencyMs": 146.2,
     "error": null
    },
    {
     "taskId": "fresh:2609.19844",
     "passed": true,
     "score": 1.0,
     "latencyMs": 131.2,
     "error": null
    },
    {
     "taskId": "fresh:2609.19942",
     "passed": false,
     "score": 0.0,
     "latencyMs": 105.0,
     "error": null
    },
    {
     "taskId": "fresh:2609.20050",
     "passed": false,
     "score": 0.0,
     "latencyMs": 209.6,
     "error": null
    },
    {
     "taskId": "fresh:2609.20131",
     "passed": false,
     "score": 0.0,
     "latencyMs": 132.9,
     "error": null
    },
    {
     "taskId": "fresh:2609.20563",
     "passed": false,
     "score": 0.0,
     "latencyMs": 262.6,
     "error": null
    },
    {
     "taskId": "fresh:2609.20807",
     "passed": true,
     "score": 1.0,
     "latencyMs": 194.9,
     "error": null
    },
    {
     "taskId": "fresh:2609.20814",
     "passed": false,
     "score": 0.0,
     "latencyMs": 169.9,
     "error": null
    },
    {
     "taskId": "fresh:2609.20411",
     "passed": false,
     "score": 0.0,
     "latencyMs": 277.9,
     "error": null
    },
    {
     "taskId": "month:2608.21662",
     "passed": false,
     "score": 0.0,
     "latencyMs": 113.1,
     "error": null
    },
    {
     "taskId": "month:2608.21664",
     "passed": false,
     "score": 0.0,
     "latencyMs": 111.7,
     "error": null
    },
    {
     "taskId": "month:2608.21668",
     "passed": true,
     "score": 1.0,
     "latencyMs": 107.3,
     "error": null
    },
    {
     "taskId": "month:2608.21673",
     "passed": true,
     "score": 1.0,
     "latencyMs": 108.8,
     "error": null
    },
    {
     "taskId": "month:2608.21677",
     "passed": true,
     "score": 1.0,
     "latencyMs": 115.6,
     "error": null
    },
    {
     "taskId": "month:2608.21690",
     "passed": true,
     "score": 1.0,
     "latencyMs": 111.3,
     "error": null
    },
    {
     "taskId": "month:2608.21558",
     "passed": false,
     "score": 0.0,
     "latencyMs": 122.8,
     "error": null
    },
    {
     "taskId": "month:2608.21559",
     "passed": false,
     "score": 0.0,
     "latencyMs": 114.7,
     "error": null
    },
    {
     "taskId": "month:2608.21601",
     "passed": true,
     "score": 1.0,
     "latencyMs": 113.8,
     "error": null
    },
    {
     "taskId": "month:2608.21606",
     "passed": false,
     "score": 0.0,
     "latencyMs": 165.1,
     "error": null
    },
    {
     "taskId": "month:2608.21656",
     "passed": false,
     "score": 0.0,
     "latencyMs": 231.5,
     "error": null
    },
    {
     "taskId": "month:2608.21243",
     "passed": false,
     "score": 0.0,
     "latencyMs": 111.6,
     "error": null
    },
    {
     "taskId": "month:2608.21252",
     "passed": false,
     "score": 0.0,
     "latencyMs": 140.7,
     "error": null
    },
    {
     "taskId": "month:2608.21274",
     "passed": false,
     "score": 0.3333,
     "latencyMs": 134.2,
     "error": null
    },
    {
     "taskId": "month:2608.21529",
     "passed": true,
     "score": 1.0,
     "latencyMs": 114.1,
     "error": null
    },
    {
     "taskId": "month:2608.21641",
     "passed": true,
     "score": 1.0,
     "latencyMs": 114.4,
     "error": null
    },
    {
     "taskId": "month:2608.21652",
     "passed": false,
     "score": 0.0,
     "latencyMs": 241.7,
     "error": null
    },
    {
     "taskId": "month:2608.21653",
     "passed": true,
     "score": 1.0,
     "latencyMs": 281.2,
     "error": null
    },
    {
     "taskId": "month:2608.21660",
     "passed": false,
     "score": 0.0,
     "latencyMs": 114.7,
     "error": null
    },
    {
     "taskId": "month:2608.21678",
     "passed": false,
     "score": 0.0,
     "latencyMs": 126.2,
     "error": null
    },
    {
     "taskId": "year:2509.18439",
     "passed": false,
     "score": 0.0,
     "latencyMs": 231.9,
     "error": null
    },
    {
     "taskId": "year:2509.18447",
     "passed": true,
     "score": 1.0,
     "latencyMs": 104.9,
     "error": null
    },
    {
     "taskId": "year:2509.18458",
     "passed": true,
     "score": 1.0,
     "latencyMs": 310.4,
     "error": null
    },
    {
     "taskId": "year:2509.18461",
     "passed": true,
     "score": 1.0,
     "latencyMs": 133.6,
     "error": null
    },
    {
     "taskId": "year:2509.18467",
     "passed": true,
     "score": 1.0,
     "latencyMs": 160.1,
     "error": null
    },
    {
     "taskId": "year:2509.20388",
     "passed": false,
     "score": 0.0,
     "latencyMs": 122.0,
     "error": null
    },
    {
     "taskId": "year:2509.18436",
     "passed": false,
     "score": 0.0,
     "latencyMs": 143.3,
     "error": null
    },
    {
     "taskId": "year:2510.01225",
     "passed": true,
     "score": 1.0,
     "latencyMs": 147.6,
     "error": null
    },
    {
     "taskId": "year:2510.01226",
     "passed": true,
     "score": 1.0,
     "latencyMs": 233.9,
     "error": null
    },
    {
     "taskId": "year:2509.17918",
     "passed": true,
     "score": 1.0,
     "latencyMs": 116.6,
     "error": null
    },
    {
     "taskId": "year:2509.18054",
     "passed": true,
     "score": 1.0,
     "latencyMs": 242.9,
     "error": null
    },
    {
     "taskId": "year:2509.18091",
     "passed": true,
     "score": 1.0,
     "latencyMs": 116.8,
     "error": null
    },
    {
     "taskId": "year:2509.18095",
     "passed": false,
     "score": 0.0,
     "latencyMs": 279.4,
     "error": null
    },
    {
     "taskId": "year:2509.21371",
     "passed": true,
     "score": 1.0,
     "latencyMs": 152.0,
     "error": null
    },
    {
     "taskId": "year:2509.18463",
     "passed": false,
     "score": 0.0,
     "latencyMs": 145.3,
     "error": null
    },
    {
     "taskId": "year:2509.18469",
     "passed": false,
     "score": 0.0,
     "latencyMs": 140.9,
     "error": null
    },
    {
     "taskId": "year:2509.18470",
     "passed": true,
     "score": 1.0,
     "latencyMs": 123.0,
     "error": null
    },
    {
     "taskId": "year:2509.18471",
     "passed": true,
     "score": 1.0,
     "latencyMs": 124.6,
     "error": null
    },
    {
     "taskId": "year:2509.18477",
     "passed": false,
     "score": 0.0,
     "latencyMs": 201.2,
     "error": null
    },
    {
     "taskId": "year:2509.18337",
     "passed": false,
     "score": 0.0,
     "latencyMs": 150.0,
     "error": null
    }
   ]
  },
  {
   "benchmarkId": "webbench-search",
   "suite": "search",
   "runId": "webbench-search-browserbase-20260919-r3",
   "startedAt": "2026-09-19T06:51:55Z",
   "finishedAt": "2026-09-19T06:55:37Z",
   "vendor": {
    "name": "Browserbase",
    "product": "Search API",
    "endpoint": "https://api.browserbase.com/v1/search",
    "configuration": "numResults 10"
   },
   "harness": "webbench.search_bench (live index)",
   "selection": "60 arXiv papers in three age buckets (submitted 2–4 days, ≈ 30 days and ≈ 365 days before the run), queried by title; one request per item, no retries; every provider saw the same items.",
   "disclosure": "Live-web suite by necessity (a search index covers the public web). Items are drawn from arXiv's API on the run date, so the set is new each run. Pass = the paper's arXiv identifier appears in the rank-1 result URL; score = reciprocal rank within the top 10. No LLM judge.",
   "metric": {
    "label": "MRR",
    "higherIsBetter": true
   },
   "aggregate": {
    "tasks": 60,
    "attempted": 60,
    "graded": 60,
    "passed": 54,
    "errors": 0,
    "meanScore": 0.9444,
    "latencyMsP50": 340.8,
    "costUsdTotal": null
   },
   "reference": [],
   "trials": [
    {
     "taskId": "fresh:2609.20812",
     "passed": true,
     "score": 1.0,
     "latencyMs": 382.2,
     "error": null
    },
    {
     "taskId": "fresh:2609.20815",
     "passed": true,
     "score": 1.0,
     "latencyMs": 358.8,
     "error": null
    },
    {
     "taskId": "fresh:2609.20816",
     "passed": true,
     "score": 1.0,
     "latencyMs": 335.4,
     "error": null
    },
    {
     "taskId": "fresh:2609.20817",
     "passed": true,
     "score": 1.0,
     "latencyMs": 342.9,
     "error": null
    },
    {
     "taskId": "fresh:2609.20820",
     "passed": true,
     "score": 1.0,
     "latencyMs": 346.0,
     "error": null
    },
    {
     "taskId": "fresh:2609.20822",
     "passed": true,
     "score": 1.0,
     "latencyMs": 340.6,
     "error": null
    },
    {
     "taskId": "fresh:2609.20784",
     "passed": true,
     "score": 1.0,
     "latencyMs": 338.8,
     "error": null
    },
    {
     "taskId": "fresh:2609.20800",
     "passed": true,
     "score": 1.0,
     "latencyMs": 342.1,
     "error": null
    },
    {
     "taskId": "fresh:2609.20804",
     "passed": true,
     "score": 1.0,
     "latencyMs": 386.0,
     "error": null
    },
    {
     "taskId": "fresh:2609.20808",
     "passed": true,
     "score": 1.0,
     "latencyMs": 339.4,
     "error": null
    },
    {
     "taskId": "fresh:2609.20821",
     "passed": true,
     "score": 1.0,
     "latencyMs": 343.0,
     "error": null
    },
    {
     "taskId": "fresh:2609.19831",
     "passed": true,
     "score": 1.0,
     "latencyMs": 339.0,
     "error": null
    },
    {
     "taskId": "fresh:2609.19844",
     "passed": true,
     "score": 1.0,
     "latencyMs": 319.2,
     "error": null
    },
    {
     "taskId": "fresh:2609.19942",
     "passed": true,
     "score": 1.0,
     "latencyMs": 344.4,
     "error": null
    },
    {
     "taskId": "fresh:2609.20050",
     "passed": true,
     "score": 1.0,
     "latencyMs": 337.6,
     "error": null
    },
    {
     "taskId": "fresh:2609.20131",
     "passed": true,
     "score": 1.0,
     "latencyMs": 332.7,
     "error": null
    },
    {
     "taskId": "fresh:2609.20563",
     "passed": true,
     "score": 1.0,
     "latencyMs": 422.2,
     "error": null
    },
    {
     "taskId": "fresh:2609.20807",
     "passed": true,
     "score": 1.0,
     "latencyMs": 351.5,
     "error": null
    },
    {
     "taskId": "fresh:2609.20814",
     "passed": true,
     "score": 1.0,
     "latencyMs": 337.9,
     "error": null
    },
    {
     "taskId": "fresh:2609.20411",
     "passed": true,
     "score": 1.0,
     "latencyMs": 344.0,
     "error": null
    },
    {
     "taskId": "month:2608.21662",
     "passed": true,
     "score": 1.0,
     "latencyMs": 338.0,
     "error": null
    },
    {
     "taskId": "month:2608.21664",
     "passed": true,
     "score": 1.0,
     "latencyMs": 338.9,
     "error": null
    },
    {
     "taskId": "month:2608.21668",
     "passed": true,
     "score": 1.0,
     "latencyMs": 748.4,
     "error": null
    },
    {
     "taskId": "month:2608.21673",
     "passed": true,
     "score": 1.0,
     "latencyMs": 353.0,
     "error": null
    },
    {
     "taskId": "month:2608.21677",
     "passed": true,
     "score": 1.0,
     "latencyMs": 337.2,
     "error": null
    },
    {
     "taskId": "month:2608.21690",
     "passed": true,
     "score": 1.0,
     "latencyMs": 343.6,
     "error": null
    },
    {
     "taskId": "month:2608.21558",
     "passed": true,
     "score": 1.0,
     "latencyMs": 320.2,
     "error": null
    },
    {
     "taskId": "month:2608.21559",
     "passed": true,
     "score": 1.0,
     "latencyMs": 330.3,
     "error": null
    },
    {
     "taskId": "month:2608.21601",
     "passed": true,
     "score": 1.0,
     "latencyMs": 338.2,
     "error": null
    },
    {
     "taskId": "month:2608.21606",
     "passed": true,
     "score": 1.0,
     "latencyMs": 337.5,
     "error": null
    },
    {
     "taskId": "month:2608.21656",
     "passed": true,
     "score": 1.0,
     "latencyMs": 339.7,
     "error": null
    },
    {
     "taskId": "month:2608.21243",
     "passed": true,
     "score": 1.0,
     "latencyMs": 338.8,
     "error": null
    },
    {
     "taskId": "month:2608.21252",
     "passed": true,
     "score": 1.0,
     "latencyMs": 312.2,
     "error": null
    },
    {
     "taskId": "month:2608.21274",
     "passed": true,
     "score": 1.0,
     "latencyMs": 339.7,
     "error": null
    },
    {
     "taskId": "month:2608.21529",
     "passed": true,
     "score": 1.0,
     "latencyMs": 318.0,
     "error": null
    },
    {
     "taskId": "month:2608.21641",
     "passed": true,
     "score": 1.0,
     "latencyMs": 327.6,
     "error": null
    },
    {
     "taskId": "month:2608.21652",
     "passed": true,
     "score": 1.0,
     "latencyMs": 315.7,
     "error": null
    },
    {
     "taskId": "month:2608.21653",
     "passed": true,
     "score": 1.0,
     "latencyMs": 347.0,
     "error": null
    },
    {
     "taskId": "month:2608.21660",
     "passed": true,
     "score": 1.0,
     "latencyMs": 361.6,
     "error": null
    },
    {
     "taskId": "month:2608.21678",
     "passed": true,
     "score": 1.0,
     "latencyMs": 422.1,
     "error": null
    },
    {
     "taskId": "year:2509.18439",
     "passed": true,
     "score": 1.0,
     "latencyMs": 365.6,
     "error": null
    },
    {
     "taskId": "year:2509.18447",
     "passed": false,
     "score": 0.5,
     "latencyMs": 345.6,
     "error": null
    },
    {
     "taskId": "year:2509.18458",
     "passed": true,
     "score": 1.0,
     "latencyMs": 352.4,
     "error": null
    },
    {
     "taskId": "year:2509.18461",
     "passed": true,
     "score": 1.0,
     "latencyMs": 336.5,
     "error": null
    },
    {
     "taskId": "year:2509.18467",
     "passed": false,
     "score": 0.3333,
     "latencyMs": 344.3,
     "error": null
    },
    {
     "taskId": "year:2509.20388",
     "passed": false,
     "score": 0.5,
     "latencyMs": 320.8,
     "error": null
    },
    {
     "taskId": "year:2509.18436",
     "passed": false,
     "score": 0.3333,
     "latencyMs": 716.4,
     "error": null
    },
    {
     "taskId": "year:2510.01225",
     "passed": true,
     "score": 1.0,
     "latencyMs": 343.4,
     "error": null
    },
    {
     "taskId": "year:2510.01226",
     "passed": true,
     "score": 1.0,
     "latencyMs": 310.8,
     "error": null
    },
    {
     "taskId": "year:2509.17918",
     "passed": true,
     "score": 1.0,
     "latencyMs": 315.8,
     "error": null
    },
    {
     "taskId": "year:2509.18054",
     "passed": true,
     "score": 1.0,
     "latencyMs": 327.8,
     "error": null
    },
    {
     "taskId": "year:2509.18091",
     "passed": true,
     "score": 1.0,
     "latencyMs": 344.2,
     "error": null
    },
    {
     "taskId": "year:2509.18095",
     "passed": true,
     "score": 1.0,
     "latencyMs": 345.4,
     "error": null
    },
    {
     "taskId": "year:2509.21371",
     "passed": true,
     "score": 1.0,
     "latencyMs": 338.4,
     "error": null
    },
    {
     "taskId": "year:2509.18463",
     "passed": true,
     "score": 1.0,
     "latencyMs": 457.3,
     "error": null
    },
    {
     "taskId": "year:2509.18469",
     "passed": false,
     "score": 0.5,
     "latencyMs": 351.6,
     "error": null
    },
    {
     "taskId": "year:2509.18470",
     "passed": true,
     "score": 1.0,
     "latencyMs": 320.1,
     "error": null
    },
    {
     "taskId": "year:2509.18471",
     "passed": true,
     "score": 1.0,
     "latencyMs": 340.9,
     "error": null
    },
    {
     "taskId": "year:2509.18477",
     "passed": true,
     "score": 1.0,
     "latencyMs": 355.8,
     "error": null
    },
    {
     "taskId": "year:2509.18337",
     "passed": false,
     "score": 0.5,
     "latencyMs": 342.3,
     "error": null
    }
   ]
  },
  {
   "benchmarkId": "webbench-interact",
   "suite": "interact",
   "runId": "webbench-interact-tinyfish-20260919-r3",
   "startedAt": "2026-09-19T06:39:55Z",
   "finishedAt": "2026-09-19T07:48:51Z",
   "vendor": {
    "name": "TinyFish",
    "product": "Web Agent API",
    "endpoint": "https://agent.tinyfish.ai/v1/automation/run-async",
    "configuration": "documented defaults, max_duration_seconds 300, no output schema"
   },
   "harness": "webbench.interact_bench v1 (hosted protocol, public tunnel)",
   "selection": "All 52 challenges of seed 7 — 52 distinct UI mechanics, one attempt each, no retries.",
   "disclosure": "Each challenge is one page with one mechanic and a one-line human request; the page never shows a success token — the server compares the state the browser submits with the target. Pass = the final submission is correct; score = first-time pass (no rejected submission before it). 25 rejected submissions across the run. A run the provider cancelled on its own before the 300 s deadline is an execution error (scores 0, shown as an error, not a failed task). Cost computed from TinyFish's metered rates ($0.016/step, $0.002/browser-minute) and the recorded steps and wall time; provider-cancelled runs report no step count, so it is a lower bound.",
   "metric": {
    "label": "First-time pass",
    "higherIsBetter": true
   },
   "aggregate": {
    "tasks": 52,
    "attempted": 52,
    "graded": 50,
    "passed": 40,
    "errors": 2,
    "meanScore": 0.7308,
    "latencyMsP50": 72700.0,
    "costUsdTotal": 16.43
   },
   "reference": [
    {
     "name": "Scripted Playwright oracle (solvability proof, not ranked)",
     "passed": 52,
     "meanScore": 1.0
    }
   ],
   "trials": [
    {
     "taskId": "table-link",
     "passed": true,
     "score": 1.0,
     "latencyMs": 73200.0,
     "error": null
    },
    {
     "taskId": "slider",
     "passed": true,
     "score": 1.0,
     "latencyMs": 72700.0,
     "error": null
    },
    {
     "taskId": "date-field",
     "passed": false,
     "score": 0.0,
     "latencyMs": 350800.0,
     "error": null
    },
    {
     "taskId": "dropdown",
     "passed": true,
     "score": 1.0,
     "latencyMs": 43100.0,
     "error": null
    },
    {
     "taskId": "checkboxes",
     "passed": true,
     "score": 1.0,
     "latencyMs": 72400.0,
     "error": null
    },
    {
     "taskId": "iframe",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41600.0,
     "error": null
    },
    {
     "taskId": "shadow-dom",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41800.0,
     "error": null
    },
    {
     "taskId": "hover-menu",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41700.0,
     "error": null
    },
    {
     "taskId": "modal",
     "passed": true,
     "score": 1.0,
     "latencyMs": 258700.0,
     "error": null
    },
    {
     "taskId": "infinite-scroll",
     "passed": true,
     "score": 1.0,
     "latencyMs": 103600.0,
     "error": null
    },
    {
     "taskId": "wizard",
     "passed": true,
     "score": 1.0,
     "latencyMs": 103400.0,
     "error": null
    },
    {
     "taskId": "scroll-to-enable",
     "passed": false,
     "score": 0.0,
     "latencyMs": 352000.0,
     "error": null
    },
    {
     "taskId": "new-tab",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41800.0,
     "error": null
    },
    {
     "taskId": "enter-to-submit",
     "passed": true,
     "score": 0.0,
     "latencyMs": 349800.0,
     "error": null
    },
    {
     "taskId": "reorder",
     "passed": true,
     "score": 0.0,
     "latencyMs": 258600.0,
     "error": null
    },
    {
     "taskId": "radio-group",
     "passed": true,
     "score": 1.0,
     "latencyMs": 42000.0,
     "error": null
    },
    {
     "taskId": "toggle-switch",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41900.0,
     "error": null
    },
    {
     "taskId": "typeahead",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41700.0,
     "error": null
    },
    {
     "taskId": "dependent-dropdowns",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41600.0,
     "error": null
    },
    {
     "taskId": "multi-select",
     "passed": false,
     "score": 0.0,
     "latencyMs": 351900.0,
     "error": null
    },
    {
     "taskId": "drag-and-drop",
     "passed": false,
     "score": 0.0,
     "latencyMs": 381200.0,
     "error": null
    },
    {
     "taskId": "tabs",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41700.0,
     "error": null
    },
    {
     "taskId": "accordion",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41600.0,
     "error": null
    },
    {
     "taskId": "pagination",
     "passed": true,
     "score": 1.0,
     "latencyMs": 320600.0,
     "error": null
    },
    {
     "taskId": "sort-table",
     "passed": true,
     "score": 1.0,
     "latencyMs": 134600.0,
     "error": null
    },
    {
     "taskId": "search-list",
     "passed": true,
     "score": 1.0,
     "latencyMs": 319100.0,
     "error": null
    },
    {
     "taskId": "hover-tooltip",
     "passed": false,
     "score": 0.0,
     "latencyMs": 319900.0,
     "error": null
    },
    {
     "taskId": "context-menu",
     "passed": false,
     "score": 0.0,
     "latencyMs": 350700.0,
     "error": null
    },
    {
     "taskId": "dblclick-edit",
     "passed": false,
     "score": 0.0,
     "latencyMs": 350500.0,
     "error": null
    },
    {
     "taskId": "keyboard-shortcut",
     "passed": false,
     "score": null,
     "latencyMs": 196200.0,
     "error": "cancelled by the provider before the deadline"
    },
    {
     "taskId": "stepper",
     "passed": false,
     "score": null,
     "latencyMs": 41700.0,
     "error": "cancelled by the provider before the deadline"
    },
    {
     "taskId": "time-field",
     "passed": false,
     "score": 0.0,
     "latencyMs": 103800.0,
     "error": null
    },
    {
     "taskId": "dual-range",
     "passed": true,
     "score": 1.0,
     "latencyMs": 72500.0,
     "error": null
    },
    {
     "taskId": "nested-menu",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41900.0,
     "error": null
    },
    {
     "taskId": "virtualised-list",
     "passed": true,
     "score": 1.0,
     "latencyMs": 350000.0,
     "error": null
    },
    {
     "taskId": "carousel",
     "passed": true,
     "score": 1.0,
     "latencyMs": 72700.0,
     "error": null
    },
    {
     "taskId": "undo-toast",
     "passed": true,
     "score": 1.0,
     "latencyMs": 289100.0,
     "error": null
    },
    {
     "taskId": "type-to-confirm",
     "passed": true,
     "score": 1.0,
     "latencyMs": 320400.0,
     "error": null
    },
    {
     "taskId": "password-rules",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41800.0,
     "error": null
    },
    {
     "taskId": "otp-boxes",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41900.0,
     "error": null
    },
    {
     "taskId": "currency-input",
     "passed": true,
     "score": 1.0,
     "latencyMs": 42100.0,
     "error": null
    },
    {
     "taskId": "rich-text",
     "passed": false,
     "score": 0.0,
     "latencyMs": 351400.0,
     "error": null
    },
    {
     "taskId": "color-input",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41800.0,
     "error": null
    },
    {
     "taskId": "show-more",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41900.0,
     "error": null
    },
    {
     "taskId": "custom-combobox",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41800.0,
     "error": null
    },
    {
     "taskId": "calendar-widget",
     "passed": true,
     "score": 1.0,
     "latencyMs": 134400.0,
     "error": null
    },
    {
     "taskId": "bulk-select",
     "passed": true,
     "score": 1.0,
     "latencyMs": 72600.0,
     "error": null
    },
    {
     "taskId": "sign-in",
     "passed": true,
     "score": 1.0,
     "latencyMs": 351300.0,
     "error": null
    },
    {
     "taskId": "canvas-target",
     "passed": false,
     "score": 0.0,
     "latencyMs": 380900.0,
     "error": null
    },
    {
     "taskId": "conditional-field",
     "passed": true,
     "score": 1.0,
     "latencyMs": 72600.0,
     "error": null
    },
    {
     "taskId": "horizontal-scroll",
     "passed": true,
     "score": 1.0,
     "latencyMs": 41800.0,
     "error": null
    },
    {
     "taskId": "load-more",
     "passed": true,
     "score": 1.0,
     "latencyMs": 72600.0,
     "error": null
    }
   ]
  }
 ]
}
