{
  "name": "Personal Agent Bench results",
  "url": "https://personalagentbench.com/results/",
  "publisher": "Zentor",
  "method": "Every figure is a share of tasks completed, with a 95% interval and the number of scored tasks it rests on. There is no combined score and no ranking, because a rate without its interval and its sample size is not a result. These September rates describe adapted runtimes using the exam model, on differing scored subsets; they are not consumer-product end-to-end performance.",
  "provenance": "These figures come from the team running the exam. The bench repository deliberately stopped tracking generated batch records in September, on the grounds that it holds the inputs a run needs rather than the outputs a run produces, so there is no published record behind these numbers for us or anyone else to check them against. We are printing them anyway, with that said plainly, because the alternative is printing nothing and pretending we have no numbers. If the underlying batches are ever published we will reconcile against them and say what changed.",
  "batches": [
    {
      "id": "first-batch",
      "label": "First batch",
      "as_of": "2026-09-22",
      "same_tasks_for_all": false,
      "note": "Each product answered its own draw of tasks, so these rates are not directly comparable with each other.",
      "rows": [
        {
          "product": "Instinct",
          "slug": "instinct",
          "status": "usable",
          "rate_pct": 43,
          "ci95_low_pct": 36,
          "ci95_high_pct": 50,
          "scored_tasks": 159,
          "runs": null,
          "note": "159 scored tasks; Pine has the largest published sample at 167. Marginal intervals alone do not establish a significant lead."
        },
        {
          "product": "Pine",
          "slug": "pine",
          "status": "usable",
          "rate_pct": 20,
          "ci95_low_pct": 14,
          "ci95_high_pct": 25,
          "scored_tasks": 167,
          "runs": null,
          "note": "More tasks scored than any other product. The September report said some tasks were being re-run; October status is unverified."
        },
        {
          "product": "Muse",
          "slug": "muse",
          "status": "usable",
          "rate_pct": 19,
          "ci95_low_pct": 13,
          "ci95_high_pct": 25,
          "scored_tasks": 90,
          "runs": null,
          "note": "This is the figure after we fixed our own adapter. The September report said a further 83 tasks were being re-run; October status is unverified."
        },
        {
          "product": "Town",
          "slug": "town",
          "status": "withheld",
          "rate_pct": null,
          "ci95_low_pct": null,
          "ci95_high_pct": null,
          "scored_tasks": null,
          "runs": null,
          "note": "Withheld. The figure we were given does not reconcile with the only records we can check: five batches for this product survive in the bench repository's history and all five were refused for incomplete domain coverage, giving roughly 13% across 30 scorable tasks. We are not publishing a number while our own evidence disagrees with it. Asked and pending."
        },
        {
          "product": "Grok",
          "slug": "grok",
          "status": "pending",
          "rate_pct": null,
          "ci95_low_pct": null,
          "ci95_high_pct": null,
          "scored_tasks": null,
          "runs": null,
          "note": "In the exam, no published figure yet. We have not taken this one apart at the runtime level either, so it has scores coming but no teardown."
        }
      ]
    },
    {
      "id": "same-tasks",
      "label": "The 09-21 to 09-22 records, filtered",
      "as_of": "2026-09-22",
      "same_tasks_for_all": true,
      "common_tasks": 114,
      "note": "A second measurement, kept beside the first rather than replacing it. Every product answered the same 114 tasks, which the table above does not: those rates rest on different tasks as well as on different sample sizes, so they were never strictly comparable with each other. These are replicas of product runtimes using the same substituted GLM 5.3 flash model, not shipping consumer products measured end to end. Not a fresh result. These are older builds judged under older rules, filtered down from roughly 5,600 attempts by eight rules, each with its own count. The filter that drops attempts which never reached the exam removes over 400 from Pine and over 400 from Muse, and if those were the products declining to act rather than a broken entry, Pine lands near 22% and Muse near 24%. Supplied transcripts have not been republished. The delivery contained 1649 transcript files for 2076 attempts, with 712 attempts sharing files after filename collisions; complete per-attempt provenance is not established.",
      "rows": [
        {
          "product": "Instinct",
          "slug": "instinct",
          "status": "usable",
          "rate_pct": 52,
          "ci95_low_pct": 45,
          "ci95_high_pct": 61,
          "scored_tasks": null,
          "runs": 380,
          "note": ""
        },
        {
          "product": "Muse",
          "slug": "muse",
          "status": "usable",
          "rate_pct": 40,
          "ci95_low_pct": 33,
          "ci95_high_pct": 46,
          "scored_tasks": null,
          "runs": 637,
          "note": ""
        },
        {
          "product": "Town",
          "slug": "town",
          "status": "usable",
          "rate_pct": 37,
          "ci95_low_pct": 30,
          "ci95_high_pct": 44,
          "scored_tasks": null,
          "runs": 513,
          "note": ""
        },
        {
          "product": "Pine",
          "slug": "pine",
          "status": "usable",
          "rate_pct": 30,
          "ci95_low_pct": 23,
          "ci95_high_pct": 36,
          "scored_tasks": null,
          "runs": 546,
          "note": ""
        }
      ]
    }
  ]
}