{
  "schema": "aig.public-measurement-extract/1",
  "notice": "Allowlisted extract, not an unchanged original. Local paths, endpoints, process IDs, generated content and free-text runtime errors are omitted. Numeric measurements are unchanged. Public checksums cover these extracts, not the original seal.",
  "source_seal_digest": "sha256:3365ae1c1cefa521adf5aba78b944df895378816b1b45d68cc84c13e3729958b",
  "run_id": "20261002T215940Z-qwen2.5-coder-1.5b-q4km-m4pro24-ollama-ctx4k-c1--a65ffba1",
  "model": {
    "artifact_size_gb": 0.99,
    "family": "Qwen2.5-Coder",
    "lab_key": "ollama/qwen2.5-coder:1.5b/sha256:29d8c98fa6b0",
    "name": "Qwen2.5 Coder 1.5B",
    "parameter_size": "1.5B",
    "quantization": "Q4_K_M",
    "runtime_ref": "qwen2.5-coder:1.5b"
  },
  "hardware": {
    "chip": "Apple M4 Pro",
    "lab_key": "apple-m4-pro-24gb",
    "memory_gib": 24,
    "memory_kind": "unified",
    "os": "macOS 15.5"
  },
  "runtime": {
    "id": "ollama",
    "server_parallel_slots": 1,
    "version": "0.35.0"
  },
  "tested_at": "2026-10-02",
  "methodology_version": "1.0.0",
  "config": {
    "concurrency": 1,
    "context": 4096,
    "max_output_tokens": 1024,
    "seed": 42,
    "temperature": 0
  },
  "workload": {
    "definition_sha256": "cacc5b92ba360b5a02c0ea6c84d5ddadf52a6223cffc8dbcb19387d076363d8e",
    "id": "coding",
    "version": "1.0.0"
  },
  "identity_checks": {
    "artifact_hash": {
      "ok": true
    },
    "effective_context": {
      "ok": true
    },
    "manifest_digest": {
      "ok": true
    },
    "memory_sampling_target": {
      "ok": true
    },
    "model_resident": {
      "ok": true
    },
    "no_contention_during_run": {
      "ok": true
    },
    "no_reload_during_run": {
      "ok": true
    },
    "serving_requested_artifact": {
      "ok": true
    }
  },
  "artifact_digest": "sha256:29d8c98fa6b098e200069bfb88b9508dc3e85586d20cba59f8dda9a808165104",
  "server_parallel_slots": 1,
  "host": {
    "captured_at": "2026-10-02T21:59:40+00:00",
    "cpu": {
      "brand": {
        "method": "sysctl machdep.cpu.brand_string",
        "value": "Apple M4 Pro"
      },
      "efficiency_cores": {
        "method": "sysctl hw.perflevel1.physicalcpu",
        "value": 4
      },
      "logical_cores": {
        "method": "sysctl hw.logicalcpu",
        "value": 12
      },
      "performance_cores": {
        "method": "sysctl hw.perflevel0.physicalcpu",
        "value": 8
      }
    },
    "gpu": {
      "cores": {
        "method": "system_profiler SPDisplaysDataType sppci_cores",
        "value": 16
      },
      "name": {
        "method": "Apple silicon: the GPU is part of the SoC named by the CPU brand",
        "value": "Apple M4 Pro"
      }
    },
    "memory": {
      "free_percent": {
        "method": "memory_pressure -Q",
        "value": 76
      },
      "kind": "unified",
      "pressure_level": {
        "method": "sysctl kern.memorystatus_vm_pressure_level (1 normal, 2 warn, 4 critical)",
        "value": 1
      },
      "total_bytes": {
        "method": "sysctl hw.memsize",
        "value": 25769803776
      }
    },
    "os": {
      "build": "24F74",
      "machine": "arm64",
      "product": "macOS",
      "release": "24.5.0",
      "system": "Darwin",
      "version": "15.5"
    },
    "harness": {
      "git_commit": {
        "method": "git rev-parse HEAD",
        "value": "c3cdc057f3b7f3137d64ad784e8b58ceb8b0b821"
      },
      "lab_tree_dirty": {
        "method": "git status --porcelain -- lab/src lab/pyproject.toml (the measuring code)",
        "value": false
      },
      "name": "aiglab",
      "version": "1.0.0"
    },
    "power_source": {
      "method": "pmset -g batt",
      "value": "AC Power"
    }
  },
  "confidence": "medium",
  "confidence_reasons": [
    "5 included measured repetitions",
    "ttft_ms has flagged outliers [0, 4]"
  ],
  "environment": {
    "pressureLevel": 1,
    "freePercent": 76,
    "loadAverage1m": 6.25
  },
  "warnings": [
    "ttft_ms has flagged outliers [0, 4]"
  ],
  "failure_summary": [
    {
      "category": "checker_failure",
      "label": "Checker failed",
      "count": 10
    }
  ],
  "runtime_completion": {
    "requests_failed": 0,
    "requests_total": 15,
    "status": "completed"
  },
  "task_success": {
    "rate": 0.3333333333333333,
    "tasks_succeeded": 5,
    "tasks_total": 15
  },
  "metrics": {
    "aggregate_output_tokens_per_s": {
      "all": {
        "cv": 0.020397739669976198,
        "max": 138.11759664395737,
        "mean": 134.61478093771814,
        "median": 134.5103931179602,
        "min": 130.59652620859464,
        "n": 5,
        "stdev": 2.745837257298449
      },
      "included": {
        "cv": 0.020397739669976198,
        "max": 138.11759664395737,
        "mean": 134.61478093771814,
        "median": 134.5103931179602,
        "min": 130.59652620859464,
        "n": 5,
        "stdev": 2.745837257298449
      },
      "outliers": [],
      "status": "measured",
      "unit": "tokens/s",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 134.04736586869777
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 130.59652620859464
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 134.5103931179602
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 138.11759664395737
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 135.80202284938073
        }
      ]
    },
    "decode_tokens_per_s": {
      "all": {
        "cv": 0.017648929994107117,
        "max": 155.91461194536254,
        "mean": 152.1912693776357,
        "median": 152.45550869616858,
        "min": 149.21229786938719,
        "n": 5,
        "stdev": 2.686013058960191
      },
      "included": {
        "cv": 0.017648929994107117,
        "max": 155.91461194536254,
        "mean": 152.1912693776357,
        "median": 152.45550869616858,
        "min": 149.21229786938719,
        "n": 5,
        "stdev": 2.686013058960191
      },
      "outliers": [],
      "status": "measured",
      "unit": "tokens/s",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 152.45550869616858
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 149.21229786938719
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 150.02223543846677
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 155.91461194536254
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 153.35169293879352
        }
      ]
    },
    "peak_phys_footprint_bytes": {
      "all": {
        "cv": 0.1001140596978035,
        "max": 391118848,
        "mean": 345191219.2,
        "median": 342884352,
        "min": 304087040,
        "n": 5,
        "stdev": 34558494.32614637
      },
      "included": {
        "cv": 0.1001140596978035,
        "max": 391118848,
        "mean": 345191219.2,
        "median": 342884352,
        "min": 304087040,
        "n": 5,
        "stdev": 34558494.32614637
      },
      "outliers": [],
      "status": "measured",
      "unit": "bytes",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 304087040
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 321912832
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 342884352
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 365953024
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 391118848
        }
      ]
    },
    "peak_rss_bytes": {
      "all": {
        "cv": 0.0268441340685715,
        "max": 1414987776,
        "mean": 1366930227.2,
        "median": 1364344832,
        "min": 1322237952,
        "n": 5,
        "stdev": 36694058.281339705
      },
      "included": {
        "cv": 0.0268441340685715,
        "max": 1414987776,
        "mean": 1366930227.2,
        "median": 1364344832,
        "min": 1322237952,
        "n": 5,
        "stdev": 36694058.281339705
      },
      "outliers": [],
      "status": "measured",
      "unit": "bytes",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 1322237952
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 1343389696
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 1364344832
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 1389690880
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 1414987776
        }
      ]
    },
    "prompt_cached_tokens_total": {
      "all": {
        "cv": 0,
        "max": 140,
        "mean": 140,
        "median": 140,
        "min": 140,
        "n": 5,
        "stdev": 0
      },
      "included": {
        "cv": 0,
        "max": 140,
        "mean": 140,
        "median": 140,
        "min": 140,
        "n": 5,
        "stdev": 0
      },
      "outliers": [],
      "status": "measured",
      "unit": "tokens",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 140
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 140
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 140
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 140
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 140
        }
      ]
    },
    "prompt_eval_ms": {
      "all": {
        "cv": 0.005444609483163487,
        "max": 73.948,
        "mean": 73.344,
        "median": 73.178,
        "min": 72.942,
        "n": 5,
        "stdev": 0.39932943793314274
      },
      "included": {
        "cv": 0.005444609483163487,
        "max": 73.948,
        "mean": 73.344,
        "median": 73.178,
        "min": 72.942,
        "n": 5,
        "stdev": 0.39932943793314274
      },
      "outliers": [],
      "status": "measured",
      "unit": "ms",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 73.948
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 72.942
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 73.178
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 73.122
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 73.53
        }
      ]
    },
    "prompt_tokens_max": {
      "all": {
        "cv": 0,
        "max": 165,
        "mean": 165,
        "median": 165,
        "min": 165,
        "n": 5,
        "stdev": 0
      },
      "included": {
        "cv": 0,
        "max": 165,
        "mean": 165,
        "median": 165,
        "min": 165,
        "n": 5,
        "stdev": 0
      },
      "outliers": [],
      "status": "measured",
      "unit": "tokens",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 165
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 165
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 165
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 165
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 165
        }
      ]
    },
    "rep_wall_s": {
      "all": {
        "cv": 0.020513089281079273,
        "max": 3.292583749993355,
        "mean": 3.1953694333933527,
        "median": 3.1967789999907836,
        "min": 3.11328904099355,
        "n": 5,
        "stdev": 0.06554689847322953
      },
      "included": {
        "cv": 0.020513089281079273,
        "max": 3.292583749993355,
        "mean": 3.1953694333933527,
        "median": 3.1967789999907836,
        "min": 3.11328904099355,
        "n": 5,
        "stdev": 0.06554689847322953
      },
      "outliers": [],
      "status": "measured",
      "unit": "s",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 3.2078213339991635
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 3.292583749993355
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 3.1967789999907836
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 3.11328904099355
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 3.1663740419899113
        }
      ]
    },
    "success_rate": {
      "all": {
        "cv": 0,
        "max": 0.3333333333333333,
        "mean": 0.3333333333333333,
        "median": 0.3333333333333333,
        "min": 0.3333333333333333,
        "n": 5,
        "stdev": 0
      },
      "included": {
        "cv": 0,
        "max": 0.3333333333333333,
        "mean": 0.3333333333333333,
        "median": 0.3333333333333333,
        "min": 0.3333333333333333,
        "n": 5,
        "stdev": 0
      },
      "outliers": [],
      "status": "measured",
      "unit": "fraction",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 0.3333333333333333
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 0.3333333333333333
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 0.3333333333333333
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 0.3333333333333333
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 0.3333333333333333
        }
      ]
    },
    "task_completion_s": {
      "all": {
        "cv": 0.026160982292590892,
        "max": 1.2225812499964377,
        "mean": 1.174080883595161,
        "median": 1.1629973749950295,
        "min": 1.1431112089921953,
        "n": 5,
        "stdev": 0.030715109205802477
      },
      "included": {
        "cv": 0.026160982292590892,
        "max": 1.2225812499964377,
        "mean": 1.174080883595161,
        "median": 1.1629973749950295,
        "min": 1.1431112089921953,
        "n": 5,
        "stdev": 0.030715109205802477
      },
      "outliers": [],
      "status": "measured",
      "unit": "s",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 1.1629973749950295
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 1.2225812499964377
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 1.183479458995862
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 1.1431112089921953
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 1.1582351249962812
        }
      ]
    },
    "tool_latency_ms": {
      "status": "unavailable",
      "unit": "ms"
    },
    "ttft_ms": {
      "all": {
        "cv": 0.011785161076008747,
        "max": 78.7825419974979,
        "mean": 77.60367500013672,
        "median": 77.00037500762846,
        "min": 76.89854099589866,
        "n": 5,
        "stdev": 0.9145718099668443
      },
      "included": {
        "cv": 0.011785161076008747,
        "max": 78.7825419974979,
        "mean": 77.60367500013672,
        "median": 77.00037500762846,
        "min": 76.89854099589866,
        "n": 5,
        "stdev": 0.9145718099668443
      },
      "outliers": [
        0,
        4
      ],
      "status": "measured",
      "unit": "ms",
      "values": [
        {
          "excluded": false,
          "outlier": true,
          "repetition": 0,
          "value": 78.7825419974979
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 76.93141700292472
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 77.00037500762846
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 76.89854099589866
        },
        {
          "excluded": false,
          "outlier": true,
          "repetition": 4,
          "value": 78.40549999673385
        }
      ]
    }
  },
  "repetitions": [
    {
      "index": -1,
      "phase": "warmup",
      "wall_s": 3.3187360419979086,
      "metrics": {
        "aggregate_output_tokens_per_s": 129.56739992528486,
        "decode_tokens_per_s": 144.3034908560547,
        "peak_phys_footprint_bytes": 276824064,
        "peak_rss_bytes": 1291452416,
        "prompt_cached_tokens_total": 129,
        "prompt_eval_ms": 73.268,
        "prompt_tokens_max": 165,
        "rep_wall_s": 3.3187360419979086,
        "requests_failed": 0,
        "requests_total": 3,
        "success_rate": 0.3333333333333333,
        "task_completion_s": 1.228163666994078,
        "tasks_succeeded": 1,
        "tasks_total": 3,
        "tool_calls": 0,
        "tool_latency_ms": null,
        "tool_latency_ms_reason": "not applicable: workload has no tool or retrieval step",
        "ttft_ms": 77.38200000312645,
        "ttft_samples": 3
      },
      "memory": {
        "peak_phys_footprint": {
          "bound": "lower bound (maximum of samples)",
          "interval_s": 2,
          "method": "footprint -p (dirty+compressed; excludes clean mapped weights)",
          "samples": 3,
          "status": "measured",
          "value_bytes": 276824064
        },
        "peak_rss": {
          "bound": "lower bound (maximum of samples)",
          "interval_s": 0.25,
          "method": "ps -o rss= (resident set incl. mapped weights)",
          "samples": 14,
          "status": "measured",
          "value_bytes": 1291452416
        }
      },
      "outcomes": [
        {
          "check_ms": 32.13695799058769,
          "lane": 0,
          "success": false,
          "task_id": "slugify",
          "wall_ms": 696.6513329971349,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 86,
              "decode_ms": 597.842,
              "decode_tokens_per_s": 143.8507164100214,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "slugify#lane0",
              "load_ms": 0.935042,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 3,
              "prompt_eval_ms": 93.798,
              "prompt_tokens": 133,
              "runtime_total_ms": 694.583875,
              "started_at": "2026-10-02T21:59:42.041+00:00",
              "ttft_ms": 98.80020801210776,
              "wall_ms": 696.5264580067014
            }
          ]
        },
        {
          "check_ms": 37.509417001274414,
          "lane": 0,
          "success": true,
          "task_id": "merge_intervals",
          "wall_ms": 1228.163666994078,
          "failure_category": null,
          "requests": [
            {
              "completion_tokens": 168,
              "decode_ms": 1164.213,
              "decode_tokens_per_s": 144.3034908560547,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "merge_intervals#lane0",
              "load_ms": 0.972083,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 63,
              "prompt_eval_ms": 59.933,
              "prompt_tokens": 156,
              "runtime_total_ms": 1227.26675,
              "started_at": "2026-10-02T21:59:42.770+00:00",
              "ttft_ms": 63.78733299789019,
              "wall_ms": 1228.056916006608
            }
          ]
        },
        {
          "check_ms": 32.69291699689347,
          "lane": 0,
          "success": false,
          "task_id": "parse_duration",
          "wall_ms": 1244.1139580041636,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 176,
              "decode_ms": 1166.491,
              "decode_tokens_per_s": 150.87986105336432,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "parse_duration#lane0",
              "load_ms": 1.024541,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 63,
              "prompt_eval_ms": 73.268,
              "prompt_tokens": 165,
              "runtime_total_ms": 1243.122375,
              "started_at": "2026-10-02T21:59:44.036+00:00",
              "ttft_ms": 77.38200000312645,
              "wall_ms": 1244.0116250072606
            }
          ]
        }
      ]
    },
    {
      "index": 0,
      "phase": "measured",
      "wall_s": 3.2078213339991635,
      "metrics": {
        "aggregate_output_tokens_per_s": 134.04736586869777,
        "decode_tokens_per_s": 152.45550869616858,
        "peak_phys_footprint_bytes": 304087040,
        "peak_rss_bytes": 1322237952,
        "prompt_cached_tokens_total": 140,
        "prompt_eval_ms": 73.948,
        "prompt_tokens_max": 165,
        "rep_wall_s": 3.2078213339991635,
        "requests_failed": 0,
        "requests_total": 3,
        "success_rate": 0.3333333333333333,
        "task_completion_s": 1.1629973749950295,
        "tasks_succeeded": 1,
        "tasks_total": 3,
        "tool_calls": 0,
        "tool_latency_ms": null,
        "tool_latency_ms_reason": "not applicable: workload has no tool or retrieval step",
        "ttft_ms": 78.7825419974979,
        "ttft_samples": 3
      },
      "memory": {
        "peak_phys_footprint": {
          "bound": "lower bound (maximum of samples)",
          "interval_s": 2,
          "method": "footprint -p (dirty+compressed; excludes clean mapped weights)",
          "samples": 3,
          "status": "measured",
          "value_bytes": 304087040
        },
        "peak_rss": {
          "bound": "lower bound (maximum of samples)",
          "interval_s": 0.25,
          "method": "ps -o rss= (resident set incl. mapped weights)",
          "samples": 14,
          "status": "measured",
          "value_bytes": 1322237952
        }
      },
      "outcomes": [
        {
          "check_ms": 36.797459004446864,
          "lane": 0,
          "success": false,
          "task_id": "slugify",
          "wall_ms": 642.966166997212,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 86,
              "decode_ms": 564.099,
              "decode_tokens_per_s": 152.45550869616858,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "slugify#lane0",
              "load_ms": 1.052917,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 14,
              "prompt_eval_ms": 74.116,
              "prompt_tokens": 133,
              "runtime_total_ms": 641.445375,
              "started_at": "2026-10-02T21:59:45.360+00:00",
              "ttft_ms": 78.7825419974979,
              "wall_ms": 642.8152500011493
            }
          ]
        },
        {
          "check_ms": 38.403165992349386,
          "lane": 0,
          "success": true,
          "task_id": "merge_intervals",
          "wall_ms": 1162.9973749950295,
          "failure_category": null,
          "requests": [
            {
              "completion_tokens": 168,
              "decode_ms": 1098.575,
              "decode_tokens_per_s": 152.92538060669503,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "merge_intervals#lane0",
              "load_ms": 1.116667,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 63,
              "prompt_eval_ms": 60.235,
              "prompt_tokens": 156,
              "runtime_total_ms": 1162.203209,
              "started_at": "2026-10-02T21:59:46.040+00:00",
              "ttft_ms": 64.3290000007255,
              "wall_ms": 1162.9167089995462
            }
          ]
        },
        {
          "check_ms": 39.017124989186414,
          "lane": 0,
          "success": false,
          "task_id": "parse_duration",
          "wall_ms": 1237.763958008145,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 176,
              "decode_ms": 1158.613,
              "decode_tokens_per_s": 151.90577008889076,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "parse_duration#lane0",
              "load_ms": 1.488041,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 63,
              "prompt_eval_ms": 73.948,
              "prompt_tokens": 165,
              "runtime_total_ms": 1236.669166,
              "started_at": "2026-10-02T21:59:47.242+00:00",
              "ttft_ms": 78.8041250052629,
              "wall_ms": 1237.6479170052335
            }
          ]
        }
      ]
    },
    {
      "index": 1,
      "phase": "measured",
      "wall_s": 3.292583749993355,
      "metrics": {
        "aggregate_output_tokens_per_s": 130.59652620859464,
        "decode_tokens_per_s": 149.21229786938719,
        "peak_phys_footprint_bytes": 321912832,
        "peak_rss_bytes": 1343389696,
        "prompt_cached_tokens_total": 140,
        "prompt_eval_ms": 72.942,
        "prompt_tokens_max": 165,
        "rep_wall_s": 3.292583749993355,
        "requests_failed": 0,
        "requests_total": 3,
        "success_rate": 0.3333333333333333,
        "task_completion_s": 1.2225812499964377,
        "tasks_succeeded": 1,
        "tasks_total": 3,
        "tool_calls": 0,
        "tool_latency_ms": null,
        "tool_latency_ms_reason": "not applicable: workload has no tool or retrieval step",
        "ttft_ms": 76.93141700292472,
        "ttft_samples": 3
      },
      "memory": {
        "peak_phys_footprint": {
          "bound": "lower bound (maximum of samples)",
          "interval_s": 2,
          "method": "footprint -p (dirty+compressed; excludes clean mapped weights)",
          "samples": 3,
          "status": "measured",
          "value_bytes": 321912832
        },
        "peak_rss": {
          "bound": "lower bound (maximum of samples)",
          "interval_s": 0.25,
          "method": "ps -o rss= (resident set incl. mapped weights)",
          "samples": 14,
          "status": "measured",
          "value_bytes": 1343389696
        }
      },
      "outcomes": [
        {
          "check_ms": 43.624500001897104,
          "lane": 0,
          "success": false,
          "task_id": "slugify",
          "wall_ms": 656.4862499944866,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 86,
              "decode_ms": 576.36,
              "decode_tokens_per_s": 149.21229786938719,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "slugify#lane0",
              "load_ms": 0.992708,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 14,
              "prompt_eval_ms": 75.327,
              "prompt_tokens": 133,
              "runtime_total_ms": 654.94275,
              "started_at": "2026-10-02T21:59:48.568+00:00",
              "ttft_ms": 79.98633300303482,
              "wall_ms": 656.3450829999056
            }
          ]
        },
        {
          "check_ms": 30.66275001037866,
          "lane": 0,
          "success": true,
          "task_id": "merge_intervals",
          "wall_ms": 1255.8207500114804,
          "failure_category": null,
          "requests": [
            {
              "completion_tokens": 168,
              "decode_ms": 1191.072,
              "decode_tokens_per_s": 141.0494075924881,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "merge_intervals#lane0",
              "load_ms": 1.234666,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 63,
              "prompt_eval_ms": 60.141,
              "prompt_tokens": 156,
              "runtime_total_ms": 1254.794708,
              "started_at": "2026-10-02T21:59:49.269+00:00",
              "ttft_ms": 64.44958300562575,
              "wall_ms": 1255.7064580032602
            }
          ]
        },
        {
          "check_ms": 34.78154199547134,
          "lane": 0,
          "success": false,
          "task_id": "parse_duration",
          "wall_ms": 1222.5812499964377,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 176,
              "decode_ms": 1145.272,
              "decode_tokens_per_s": 153.67528412464463,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "parse_duration#lane0",
              "load_ms": 0.987166,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 63,
              "prompt_eval_ms": 72.942,
              "prompt_tokens": 165,
              "runtime_total_ms": 1221.589,
              "started_at": "2026-10-02T21:59:50.555+00:00",
              "ttft_ms": 76.93141700292472,
              "wall_ms": 1222.4519589944975
            }
          ]
        }
      ]
    },
    {
      "index": 2,
      "phase": "measured",
      "wall_s": 3.1967789999907836,
      "metrics": {
        "aggregate_output_tokens_per_s": 134.5103931179602,
        "decode_tokens_per_s": 150.02223543846677,
        "peak_phys_footprint_bytes": 342884352,
        "peak_rss_bytes": 1364344832,
        "prompt_cached_tokens_total": 140,
        "prompt_eval_ms": 73.178,
        "prompt_tokens_max": 165,
        "rep_wall_s": 3.1967789999907836,
        "requests_failed": 0,
        "requests_total": 3,
        "success_rate": 0.3333333333333333,
        "task_completion_s": 1.183479458995862,
        "tasks_succeeded": 1,
        "tasks_total": 3,
        "tool_calls": 0,
        "tool_latency_ms": null,
        "tool_latency_ms_reason": "not applicable: workload has no tool or retrieval step",
        "ttft_ms": 77.00037500762846,
        "ttft_samples": 3
      },
      "memory": {
        "peak_phys_footprint": {
          "bound": "lower bound (maximum of samples)",
          "interval_s": 2,
          "method": "footprint -p (dirty+compressed; excludes clean mapped weights)",
          "samples": 3,
          "status": "measured",
          "value_bytes": 342884352
        },
        "peak_rss": {
          "bound": "lower bound (maximum of samples)",
          "interval_s": 0.25,
          "method": "ps -o rss= (resident set incl. mapped weights)",
          "samples": 14,
          "status": "measured",
          "value_bytes": 1364344832
        }
      },
      "outcomes": [
        {
          "check_ms": 24.6119590010494,
          "lane": 0,
          "success": false,
          "task_id": "slugify",
          "wall_ms": 665.0683329935418,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 86,
              "decode_ms": 586.575,
              "decode_tokens_per_s": 146.61381749989343,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "slugify#lane0",
              "load_ms": 0.904583,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 14,
              "prompt_eval_ms": 73.954,
              "prompt_tokens": 133,
              "runtime_total_ms": 663.649708,
              "started_at": "2026-10-02T21:59:51.861+00:00",
              "ttft_ms": 78.27425000141375,
              "wall_ms": 664.9564170074882
            }
          ]
        },
        {
          "check_ms": 30.170624988386407,
          "lane": 0,
          "success": true,
          "task_id": "merge_intervals",
          "wall_ms": 1183.479458995862,
          "failure_category": null,
          "requests": [
            {
              "completion_tokens": 168,
              "decode_ms": 1119.834,
              "decode_tokens_per_s": 150.02223543846677,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "merge_intervals#lane0",
              "load_ms": 0.998542,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 63,
              "prompt_eval_ms": 59.195,
              "prompt_tokens": 156,
              "runtime_total_ms": 1182.541334,
              "started_at": "2026-10-02T21:59:52.551+00:00",
              "ttft_ms": 63.30658300430514,
              "wall_ms": 1183.3729999925708
            }
          ]
        },
        {
          "check_ms": 31.814417001442052,
          "lane": 0,
          "success": false,
          "task_id": "parse_duration",
          "wall_ms": 1213.289999999688,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 176,
              "decode_ms": 1135.933,
              "decode_tokens_per_s": 154.93871557565453,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "parse_duration#lane0",
              "load_ms": 0.97425,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 63,
              "prompt_eval_ms": 73.178,
              "prompt_tokens": 165,
              "runtime_total_ms": 1212.249458,
              "started_at": "2026-10-02T21:59:53.765+00:00",
              "ttft_ms": 77.00037500762846,
              "wall_ms": 1213.200833008159
            }
          ]
        }
      ]
    },
    {
      "index": 3,
      "phase": "measured",
      "wall_s": 3.11328904099355,
      "metrics": {
        "aggregate_output_tokens_per_s": 138.11759664395737,
        "decode_tokens_per_s": 155.91461194536254,
        "peak_phys_footprint_bytes": 365953024,
        "peak_rss_bytes": 1389690880,
        "prompt_cached_tokens_total": 140,
        "prompt_eval_ms": 73.122,
        "prompt_tokens_max": 165,
        "rep_wall_s": 3.11328904099355,
        "requests_failed": 0,
        "requests_total": 3,
        "success_rate": 0.3333333333333333,
        "task_completion_s": 1.1431112089921953,
        "tasks_succeeded": 1,
        "tasks_total": 3,
        "tool_calls": 0,
        "tool_latency_ms": null,
        "tool_latency_ms_reason": "not applicable: workload has no tool or retrieval step",
        "ttft_ms": 76.89854099589866,
        "ttft_samples": 3
      },
      "memory": {
        "peak_phys_footprint": {
          "bound": "lower bound (maximum of samples)",
          "interval_s": 2,
          "method": "footprint -p (dirty+compressed; excludes clean mapped weights)",
          "samples": 3,
          "status": "measured",
          "value_bytes": 365953024
        },
        "peak_rss": {
          "bound": "lower bound (maximum of samples)",
          "interval_s": 0.25,
          "method": "ps -o rss= (resident set incl. mapped weights)",
          "samples": 13,
          "status": "measured",
          "value_bytes": 1389690880
        }
      },
      "outcomes": [
        {
          "check_ms": 28.334292001090944,
          "lane": 0,
          "success": false,
          "task_id": "slugify",
          "wall_ms": 627.3636249970878,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 86,
              "decode_ms": 548.516,
              "decode_tokens_per_s": 156.78667532031884,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "slugify#lane0",
              "load_ms": 1.172625,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 14,
              "prompt_eval_ms": 73.726,
              "prompt_tokens": 133,
              "runtime_total_ms": 625.643542,
              "started_at": "2026-10-02T21:59:55.058+00:00",
              "ttft_ms": 78.5302089934703,
              "wall_ms": 627.2461249900516
            }
          ]
        },
        {
          "check_ms": 29.097583988914266,
          "lane": 0,
          "success": true,
          "task_id": "merge_intervals",
          "wall_ms": 1143.1112089921953,
          "failure_category": null,
          "requests": [
            {
              "completion_tokens": 168,
              "decode_ms": 1079.4,
              "decode_tokens_per_s": 155.6420233463035,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "merge_intervals#lane0",
              "load_ms": 1.17325,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 63,
              "prompt_eval_ms": 59.554,
              "prompt_tokens": 156,
              "runtime_total_ms": 1142.178208,
              "started_at": "2026-10-02T21:59:55.714+00:00",
              "ttft_ms": 63.34125000284985,
              "wall_ms": 1143.0061249993742
            }
          ]
        },
        {
          "check_ms": 29.97075000894256,
          "lane": 0,
          "success": false,
          "task_id": "parse_duration",
          "wall_ms": 1206.045582992374,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 176,
              "decode_ms": 1128.823,
              "decode_tokens_per_s": 155.91461194536254,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "parse_duration#lane0",
              "load_ms": 0.925708,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 63,
              "prompt_eval_ms": 73.122,
              "prompt_tokens": 165,
              "runtime_total_ms": 1205.068666,
              "started_at": "2026-10-02T21:59:56.886+00:00",
              "ttft_ms": 76.89854099589866,
              "wall_ms": 1205.94387500023
            }
          ]
        }
      ]
    },
    {
      "index": 4,
      "phase": "measured",
      "wall_s": 3.1663740419899113,
      "metrics": {
        "aggregate_output_tokens_per_s": 135.80202284938073,
        "decode_tokens_per_s": 153.35169293879352,
        "peak_phys_footprint_bytes": 391118848,
        "peak_rss_bytes": 1414987776,
        "prompt_cached_tokens_total": 140,
        "prompt_eval_ms": 73.53,
        "prompt_tokens_max": 165,
        "rep_wall_s": 3.1663740419899113,
        "requests_failed": 0,
        "requests_total": 3,
        "success_rate": 0.3333333333333333,
        "task_completion_s": 1.1582351249962812,
        "tasks_succeeded": 1,
        "tasks_total": 3,
        "tool_calls": 0,
        "tool_latency_ms": null,
        "tool_latency_ms_reason": "not applicable: workload has no tool or retrieval step",
        "ttft_ms": 78.40549999673385,
        "ttft_samples": 3
      },
      "memory": {
        "peak_phys_footprint": {
          "bound": "lower bound (maximum of samples)",
          "interval_s": 2,
          "method": "footprint -p (dirty+compressed; excludes clean mapped weights)",
          "samples": 3,
          "status": "measured",
          "value_bytes": 391118848
        },
        "peak_rss": {
          "bound": "lower bound (maximum of samples)",
          "interval_s": 0.25,
          "method": "ps -o rss= (resident set incl. mapped weights)",
          "samples": 13,
          "status": "measured",
          "value_bytes": 1414987776
        }
      },
      "outcomes": [
        {
          "check_ms": 27.95483299996704,
          "lane": 0,
          "success": false,
          "task_id": "slugify",
          "wall_ms": 624.0804580011172,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 86,
              "decode_ms": 545.373,
              "decode_tokens_per_s": 157.69024135774964,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "slugify#lane0",
              "load_ms": 1.080125,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 14,
              "prompt_eval_ms": 73.53,
              "prompt_tokens": 133,
              "runtime_total_ms": 622.328625,
              "started_at": "2026-10-02T21:59:58.171+00:00",
              "ttft_ms": 78.40549999673385,
              "wall_ms": 623.9809999970021
            }
          ]
        },
        {
          "check_ms": 41.92699999839533,
          "lane": 0,
          "success": true,
          "task_id": "merge_intervals",
          "wall_ms": 1158.2351249962812,
          "failure_category": null,
          "requests": [
            {
              "completion_tokens": 168,
              "decode_ms": 1095.521,
              "decode_tokens_per_s": 153.35169293879352,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "merge_intervals#lane0",
              "load_ms": 1.105625,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 63,
              "prompt_eval_ms": 58.864,
              "prompt_tokens": 156,
              "runtime_total_ms": 1157.472042,
              "started_at": "2026-10-02T21:59:58.824+00:00",
              "ttft_ms": 62.55604198668152,
              "wall_ms": 1158.1542919884669
            }
          ]
        },
        {
          "check_ms": 28.61325000412762,
          "lane": 0,
          "success": false,
          "task_id": "parse_duration",
          "wall_ms": 1235.9511670074426,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 176,
              "decode_ms": 1157.187,
              "decode_tokens_per_s": 152.09296336719996,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "parse_duration#lane0",
              "load_ms": 1.298375,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 63,
              "prompt_eval_ms": 73.832,
              "prompt_tokens": 165,
              "runtime_total_ms": 1234.929125,
              "started_at": "2026-10-02T22:00:00.024+00:00",
              "ttft_ms": 78.45654200355057,
              "wall_ms": 1235.8386249979958
            }
          ]
        }
      ]
    }
  ],
  "memory_samples": {
    "measured-0": {
      "phys_footprint": [
        [
          0.045,
          286261248
        ],
        [
          2.113,
          304087040
        ],
        [
          3.208,
          304087040
        ]
      ],
      "rss": [
        [
          0.003,
          1291452416
        ],
        [
          0.276,
          1303117824
        ],
        [
          0.536,
          1303068672
        ],
        [
          0.793,
          1311145984
        ],
        [
          1.056,
          1311113216
        ],
        [
          1.318,
          1311047680
        ],
        [
          1.58,
          1311080448
        ],
        [
          1.842,
          1311080448
        ],
        [
          2.098,
          1322237952
        ],
        [
          2.357,
          1322237952
        ],
        [
          2.612,
          1322237952
        ],
        [
          2.871,
          1322237952
        ],
        [
          3.133,
          1322237952
        ],
        [
          3.163,
          1322237952
        ]
      ]
    },
    "measured-1": {
      "phys_footprint": [
        [
          0.044,
          311427072
        ],
        [
          2.096,
          321912832
        ],
        [
          3.293,
          321912832
        ]
      ],
      "rss": [
        [
          0.003,
          1322237952
        ],
        [
          0.261,
          1334034432
        ],
        [
          0.529,
          1334034432
        ],
        [
          0.79,
          1334067200
        ],
        [
          1.047,
          1334099968
        ],
        [
          1.321,
          1334099968
        ],
        [
          1.594,
          1334099968
        ],
        [
          1.854,
          1334099968
        ],
        [
          2.114,
          1343373312
        ],
        [
          2.376,
          1343373312
        ],
        [
          2.638,
          1343373312
        ],
        [
          2.9,
          1343373312
        ],
        [
          3.163,
          1343373312
        ],
        [
          3.25,
          1343389696
        ]
      ]
    },
    "measured-2": {
      "phys_footprint": [
        [
          0.044,
          331350016
        ],
        [
          2.102,
          342884352
        ],
        [
          3.197,
          342884352
        ]
      ],
      "rss": [
        [
          0.003,
          1343389696
        ],
        [
          0.258,
          1353154560
        ],
        [
          0.52,
          1353187328
        ],
        [
          0.776,
          1353187328
        ],
        [
          1.034,
          1353187328
        ],
        [
          1.293,
          1353203712
        ],
        [
          1.549,
          1353203712
        ],
        [
          1.807,
          1353203712
        ],
        [
          2.063,
          1364344832
        ],
        [
          2.323,
          1364344832
        ],
        [
          2.585,
          1364344832
        ],
        [
          2.843,
          1364344832
        ],
        [
          3.103,
          1364344832
        ],
        [
          3.154,
          1364344832
        ]
      ]
    },
    "measured-3": {
      "phys_footprint": [
        [
          0.045,
          350224384
        ],
        [
          2.105,
          365953024
        ],
        [
          3.113,
          365953024
        ]
      ],
      "rss": [
        [
          0.003,
          1364344832
        ],
        [
          0.266,
          1374126080
        ],
        [
          0.528,
          1374126080
        ],
        [
          0.786,
          1380401152
        ],
        [
          1.043,
          1380401152
        ],
        [
          1.305,
          1380401152
        ],
        [
          1.567,
          1380401152
        ],
        [
          1.823,
          1380401152
        ],
        [
          2.083,
          1389690880
        ],
        [
          2.345,
          1389690880
        ],
        [
          2.605,
          1389690880
        ],
        [
          2.867,
          1389690880
        ],
        [
          3.069,
          1389690880
        ]
      ]
    },
    "measured-4": {
      "phys_footprint": [
        [
          0.045,
          375390208
        ],
        [
          2.115,
          391118848
        ],
        [
          3.166,
          391118848
        ]
      ],
      "rss": [
        [
          0.003,
          1389690880
        ],
        [
          0.265,
          1399455744
        ],
        [
          0.523,
          1399455744
        ],
        [
          0.786,
          1405714432
        ],
        [
          1.044,
          1405714432
        ],
        [
          1.306,
          1405714432
        ],
        [
          1.564,
          1405714432
        ],
        [
          1.825,
          1405714432
        ],
        [
          2.082,
          1414987776
        ],
        [
          2.343,
          1414987776
        ],
        [
          2.605,
          1414987776
        ],
        [
          2.866,
          1414987776
        ],
        [
          3.122,
          1414987776
        ]
      ]
    },
    "warmup--1": {
      "phys_footprint": [
        [
          0.046,
          260046848
        ],
        [
          2.099,
          276824064
        ],
        [
          3.319,
          276824064
        ]
      ],
      "rss": [
        [
          0.004,
          1268695040
        ],
        [
          0.263,
          1273561088
        ],
        [
          0.537,
          1273610240
        ],
        [
          0.792,
          1280114688
        ],
        [
          1.065,
          1281966080
        ],
        [
          1.333,
          1282015232
        ],
        [
          1.601,
          1282048000
        ],
        [
          1.87,
          1282048000
        ],
        [
          2.128,
          1291436032
        ],
        [
          2.401,
          1291436032
        ],
        [
          2.671,
          1291452416
        ],
        [
          2.94,
          1291452416
        ],
        [
          3.213,
          1291452416
        ],
        [
          3.276,
          1291452416
        ]
      ]
    }
  }
}
