{
  "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": "sha256:178dcced44782dd242c7c88e85622ee326c133f603741f9cc9b007632e301ea2",
  "run_id": "20261019T205345Z-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": "0.40.3"
  },
  "tested_at": "2026-10-19",
  "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": "2026-10-19T20:53:45+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": 45
      },
      "kind": "unified",
      "pressure_level": {
        "method": "sysctl kern.memorystatus_vm_pressure_level (1 normal, 2 warn, 4 critical)",
        "value": 2
      },
      "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": "2a4b0f67c7393b8efe34fa4466f810650c500784"
      },
      "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",
    "decode_tokens_per_s has flagged outliers [2]"
  ],
  "environment": {
    "pressureLevel": 2,
    "freePercent": 45,
    "loadAverage1m": 5.85
  },
  "warnings": [
    "decode_tokens_per_s has flagged outliers [2]",
    "Host memory pressure: warning (level 2); free memory 45%; 1-minute load 5.85."
  ],
  "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": 0.013154975312781736,
        "max": 136.8200527108999,
        "mean": 134.46531903307988,
        "median": 133.45304108532164,
        "min": 132.77290134941674,
        "n": 5,
        "stdev": 1.768887952305486
      },
      "included": {
        "cv": 0.013154975312781736,
        "max": 136.8200527108999,
        "mean": 134.46531903307988,
        "median": 133.45304108532164,
        "min": 132.77290134941674,
        "n": 5,
        "stdev": 1.768887952305486
      },
      "outliers": [],
      "status": "measured",
      "unit": "tokens/s",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 133.45304108532164
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 133.41130311936203
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 132.77290134941674
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 135.86929690039918
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 136.8200527108999
        }
      ]
    },
    "decode_tokens_per_s": {
      "all": {
        "cv": 0.011408653985215251,
        "max": 154.77950829866916,
        "mean": 153.61940140081708,
        "median": 154.11032372799878,
        "min": 150.53703210989903,
        "n": 5,
        "stdev": 1.752590595997813
      },
      "included": {
        "cv": 0.011408653985215251,
        "max": 154.77950829866916,
        "mean": 153.61940140081708,
        "median": 154.11032372799878,
        "min": 150.53703210989903,
        "n": 5,
        "stdev": 1.752590595997813
      },
      "outliers": [
        2
      ],
      "status": "measured",
      "unit": "tokens/s",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 154.0400504131074
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 154.11032372799878
        },
        {
          "excluded": false,
          "outlier": true,
          "repetition": 2,
          "value": 150.53703210989903
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 154.63009245441108
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 154.77950829866916
        }
      ]
    },
    "peak_phys_footprint_bytes": {
      "all": {
        "cv": 0.10651582179799217,
        "max": 411041792,
        "mean": 364904448,
        "median": 367001600,
        "min": 314572800,
        "n": 5,
        "stdev": 38868097.1564627
      },
      "included": {
        "cv": 0.10651582179799217,
        "max": 411041792,
        "mean": 364904448,
        "median": 367001600,
        "min": 314572800,
        "n": 5,
        "stdev": 38868097.1564627
      },
      "outliers": [],
      "status": "measured",
      "unit": "bytes",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 314572800
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 339738624
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 367001600
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 392167424
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 411041792
        }
      ]
    },
    "peak_rss_bytes": {
      "all": {
        "cv": 0.030619280953401634,
        "max": 1415659520,
        "mean": 1366478028.8,
        "median": 1369194496,
        "min": 1312817152,
        "n": 5,
        "stdev": 41840574.68047765
      },
      "included": {
        "cv": 0.030619280953401634,
        "max": 1415659520,
        "mean": 1366478028.8,
        "median": 1369194496,
        "min": 1312817152,
        "n": 5,
        "stdev": 41840574.68047765
      },
      "outliers": [],
      "status": "measured",
      "unit": "bytes",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 1312817152
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 1338245120
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 1369194496
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 1396473856
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 1415659520
        }
      ]
    },
    "prompt_cached_tokens_total": {
      "all": {
        "cv": 0,
        "max": 143,
        "mean": 143,
        "median": 143,
        "min": 143,
        "n": 5,
        "stdev": 0
      },
      "included": {
        "cv": 0,
        "max": 143,
        "mean": 143,
        "median": 143,
        "min": 143,
        "n": 5,
        "stdev": 0
      },
      "outliers": [],
      "status": "measured",
      "unit": "tokens",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 143
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 143
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 143
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 143
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 143
        }
      ]
    },
    "prompt_eval_ms": {
      "all": {
        "cv": 0.005145825691508433,
        "max": 74.053,
        "mean": 73.5518,
        "median": 73.566,
        "min": 73.102,
        "n": 5,
        "stdev": 0.3784847420966899
      },
      "included": {
        "cv": 0.005145825691508433,
        "max": 74.053,
        "mean": 73.5518,
        "median": 73.566,
        "min": 73.102,
        "n": 5,
        "stdev": 0.3784847420966899
      },
      "outliers": [],
      "status": "measured",
      "unit": "ms",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 73.566
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 74.053
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 73.102
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 73.277
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 73.761
        }
      ]
    },
    "prompt_tokens_max": {
      "all": {
        "cv": 0,
        "max": 166,
        "mean": 166,
        "median": 166,
        "min": 166,
        "n": 5,
        "stdev": 0
      },
      "included": {
        "cv": 0,
        "max": 166,
        "mean": 166,
        "median": 166,
        "min": 166,
        "n": 5,
        "stdev": 0
      },
      "outliers": [],
      "status": "measured",
      "unit": "tokens",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 166
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 166
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 166
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 166
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 166
        }
      ]
    },
    "rep_wall_s": {
      "all": {
        "cv": 0.013087452350364962,
        "max": 3.238612665911205,
        "mean": 3.1982910913648084,
        "median": 3.2221071659587324,
        "min": 3.142814167076722,
        "n": 5,
        "stdev": 0.04185748226083368
      },
      "included": {
        "cv": 0.013087452350364962,
        "max": 3.238612665911205,
        "mean": 3.1982910913648084,
        "median": 3.2221071659587324,
        "min": 3.142814167076722,
        "n": 5,
        "stdev": 0.04185748226083368
      },
      "outliers": [],
      "status": "measured",
      "unit": "s",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 3.2221071659587324
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 3.2231152079766616
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 3.238612665911205
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 3.164806249900721
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 3.142814167076722
        }
      ]
    },
    "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": 0.0028515147767895033,
        "max": 1.1578017090214416,
        "mean": 1.1536360831931234,
        "median": 1.1544269579462707,
        "min": 1.149120874935761,
        "n": 5,
        "stdev": 0.003289610338262756
      },
      "included": {
        "cv": 0.0028515147767895033,
        "max": 1.1578017090214416,
        "mean": 1.1536360831931234,
        "median": 1.1544269579462707,
        "min": 1.149120874935761,
        "n": 5,
        "stdev": 0.003289610338262756
      },
      "outliers": [],
      "status": "measured",
      "unit": "s",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 1.1544269579462707
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 1.1518624160671607
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 1.1549684579949826
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 1.1578017090214416
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 1.149120874935761
        }
      ]
    },
    "tool_latency_ms": {
      "status": "unavailable",
      "unit": "ms"
    },
    "ttft_ms": {
      "all": {
        "cv": 0.011439315194938139,
        "max": 79.27791692782193,
        "mean": 78.28881680034101,
        "median": 78.48329201806337,
        "min": 77.24620797671378,
        "n": 5,
        "stdev": 0.8955704516178692
      },
      "included": {
        "cv": 0.011439315194938139,
        "max": 79.27791692782193,
        "mean": 78.28881680034101,
        "median": 78.48329201806337,
        "min": 77.24620797671378,
        "n": 5,
        "stdev": 0.8955704516178692
      },
      "outliers": [],
      "status": "measured",
      "unit": "ms",
      "values": [
        {
          "excluded": false,
          "outlier": false,
          "repetition": 0,
          "value": 78.48329201806337
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 1,
          "value": 79.27791692782193
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 2,
          "value": 77.47837505303323
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 3,
          "value": 77.24620797671378
        },
        {
          "excluded": false,
          "outlier": false,
          "repetition": 4,
          "value": 78.95829202607274
        }
      ]
    }
  },
  "repetitions": [
    {
      "index": -1,
      "phase": "warmup",
      "wall_s": 3.2854920000536367,
      "metrics": {
        "aggregate_output_tokens_per_s": 130.8784194248472,
        "decode_tokens_per_s": 151.54809080978097,
        "peak_phys_footprint_bytes": 292552704,
        "peak_rss_bytes": 1285783552,
        "prompt_cached_tokens_total": 131,
        "prompt_eval_ms": 73.323,
        "prompt_tokens_max": 166,
        "rep_wall_s": 3.2854920000536367,
        "requests_failed": 0,
        "requests_total": 3,
        "success_rate": 0.3333333333333333,
        "task_completion_s": 1.1731843340676278,
        "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": 77.95329205691814,
        "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": 292552704
        },
        "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": 1285783552
        }
      },
      "outcomes": [
        {
          "check_ms": 42.988750035874546,
          "lane": 0,
          "success": false,
          "task_id": "slugify",
          "wall_ms": 709.4728329684585,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 86,
              "decode_ms": 580.187,
              "decode_tokens_per_s": 148.22807129425513,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "slugify#lane0",
              "load_ms": 3.53375,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 3,
              "prompt_eval_ms": 121.13,
              "prompt_tokens": 134,
              "runtime_total_ms": 708.171167,
              "started_at": "2026-10-19T20:53:47.298+00:00",
              "ttft_ms": 129.2142920428887,
              "wall_ms": 709.3135829782113
            }
          ]
        },
        {
          "check_ms": 33.49683398846537,
          "lane": 0,
          "success": true,
          "task_id": "merge_intervals",
          "wall_ms": 1173.1843340676278,
          "failure_category": null,
          "requests": [
            {
              "completion_tokens": 168,
              "decode_ms": 1108.559,
              "decode_tokens_per_s": 151.54809080978097,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "merge_intervals#lane0",
              "load_ms": 1.636917,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 64,
              "prompt_eval_ms": 59.647,
              "prompt_tokens": 157,
              "runtime_total_ms": 1172.114583,
              "started_at": "2026-10-19T20:53:48.051+00:00",
              "ttft_ms": 64.25925006624311,
              "wall_ms": 1173.071000026539
            }
          ]
        },
        {
          "check_ms": 54.36216597445309,
          "lane": 0,
          "success": false,
          "task_id": "parse_duration",
          "wall_ms": 1226.3966250466183,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 176,
              "decode_ms": 1148.249,
              "decode_tokens_per_s": 153.27685893913252,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "parse_duration#lane0",
              "load_ms": 1.790292,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 64,
              "prompt_eval_ms": 73.323,
              "prompt_tokens": 166,
              "runtime_total_ms": 1225.557292,
              "started_at": "2026-10-19T20:53:49.258+00:00",
              "ttft_ms": 77.95329205691814,
              "wall_ms": 1226.314292056486
            }
          ]
        }
      ]
    },
    {
      "index": 0,
      "phase": "measured",
      "wall_s": 3.2221071659587324,
      "metrics": {
        "aggregate_output_tokens_per_s": 133.45304108532164,
        "decode_tokens_per_s": 154.0400504131074,
        "peak_phys_footprint_bytes": 314572800,
        "peak_rss_bytes": 1312817152,
        "prompt_cached_tokens_total": 143,
        "prompt_eval_ms": 73.566,
        "prompt_tokens_max": 166,
        "rep_wall_s": 3.2221071659587324,
        "requests_failed": 0,
        "requests_total": 3,
        "success_rate": 0.3333333333333333,
        "task_completion_s": 1.1544269579462707,
        "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": 78.48329201806337,
        "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": 314572800
        },
        "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": 1312817152
        }
      },
      "outcomes": [
        {
          "check_ms": 54.43270900286734,
          "lane": 0,
          "success": false,
          "task_id": "slugify",
          "wall_ms": 643.3107909979299,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 86,
              "decode_ms": 563.898,
              "decode_tokens_per_s": 152.50985107235707,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "slugify#lane0",
              "load_ms": 1.568916,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 15,
              "prompt_eval_ms": 74.056,
              "prompt_tokens": 134,
              "runtime_total_ms": 641.725833,
              "started_at": "2026-10-19T20:53:50.584+00:00",
              "ttft_ms": 79.12195799872279,
              "wall_ms": 643.1468330556527
            }
          ]
        },
        {
          "check_ms": 48.655209015123546,
          "lane": 0,
          "success": true,
          "task_id": "merge_intervals",
          "wall_ms": 1154.4269579462707,
          "failure_category": null,
          "requests": [
            {
              "completion_tokens": 168,
              "decode_ms": 1088.487,
              "decode_tokens_per_s": 154.34267933379084,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "merge_intervals#lane0",
              "load_ms": 1.775708,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 64,
              "prompt_eval_ms": 60.419,
              "prompt_tokens": 157,
              "runtime_total_ms": 1153.448375,
              "started_at": "2026-10-19T20:53:51.282+00:00",
              "ttft_ms": 65.68408291786909,
              "wall_ms": 1154.3280829209834
            }
          ]
        },
        {
          "check_ms": 54.747542017139494,
          "lane": 0,
          "success": false,
          "task_id": "parse_duration",
          "wall_ms": 1221.4974999660626,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 176,
              "decode_ms": 1142.56,
              "decode_tokens_per_s": 154.0400504131074,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "parse_duration#lane0",
              "load_ms": 1.685583,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 64,
              "prompt_eval_ms": 73.566,
              "prompt_tokens": 166,
              "runtime_total_ms": 1220.432875,
              "started_at": "2026-10-19T20:53:52.485+00:00",
              "ttft_ms": 78.48329201806337,
              "wall_ms": 1221.3863750221208
            }
          ]
        }
      ]
    },
    {
      "index": 1,
      "phase": "measured",
      "wall_s": 3.2231152079766616,
      "metrics": {
        "aggregate_output_tokens_per_s": 133.41130311936203,
        "decode_tokens_per_s": 154.11032372799878,
        "peak_phys_footprint_bytes": 339738624,
        "peak_rss_bytes": 1338245120,
        "prompt_cached_tokens_total": 143,
        "prompt_eval_ms": 74.053,
        "prompt_tokens_max": 166,
        "rep_wall_s": 3.2231152079766616,
        "requests_failed": 0,
        "requests_total": 3,
        "success_rate": 0.3333333333333333,
        "task_completion_s": 1.1518624160671607,
        "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": 79.27791692782193,
        "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": 339738624
        },
        "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": 1338245120
        }
      },
      "outcomes": [
        {
          "check_ms": 52.600708906538785,
          "lane": 0,
          "success": false,
          "task_id": "slugify",
          "wall_ms": 653.6050830036402,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 86,
              "decode_ms": 573.882,
              "decode_tokens_per_s": 149.85659072771057,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "slugify#lane0",
              "load_ms": 1.44375,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 15,
              "prompt_eval_ms": 74.182,
              "prompt_tokens": 134,
              "runtime_total_ms": 652.189708,
              "started_at": "2026-10-19T20:53:53.806+00:00",
              "ttft_ms": 79.42191592883319,
              "wall_ms": 653.4649579552934
            }
          ]
        },
        {
          "check_ms": 46.97374999523163,
          "lane": 0,
          "success": true,
          "task_id": "merge_intervals",
          "wall_ms": 1151.8624160671607,
          "failure_category": null,
          "requests": [
            {
              "completion_tokens": 168,
              "decode_ms": 1086.169,
              "decode_tokens_per_s": 154.67206300308698,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "merge_intervals#lane0",
              "load_ms": 2.358125,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 64,
              "prompt_eval_ms": 60.197,
              "prompt_tokens": 157,
              "runtime_total_ms": 1150.932042,
              "started_at": "2026-10-19T20:53:54.512+00:00",
              "ttft_ms": 65.47866691835225,
              "wall_ms": 1151.769374962896
            }
          ]
        },
        {
          "check_ms": 51.516792038455606,
          "lane": 0,
          "success": false,
          "task_id": "parse_duration",
          "wall_ms": 1221.4690420078114,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 176,
              "decode_ms": 1142.039,
              "decode_tokens_per_s": 154.11032372799878,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "parse_duration#lane0",
              "load_ms": 1.750625,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 64,
              "prompt_eval_ms": 74.053,
              "prompt_tokens": 166,
              "runtime_total_ms": 1220.565291,
              "started_at": "2026-10-19T20:53:55.711+00:00",
              "ttft_ms": 79.27791692782193,
              "wall_ms": 1221.3888339465484
            }
          ]
        }
      ]
    },
    {
      "index": 2,
      "phase": "measured",
      "wall_s": 3.238612665911205,
      "metrics": {
        "aggregate_output_tokens_per_s": 132.77290134941674,
        "decode_tokens_per_s": 150.53703210989903,
        "peak_phys_footprint_bytes": 367001600,
        "peak_rss_bytes": 1369194496,
        "prompt_cached_tokens_total": 143,
        "prompt_eval_ms": 73.102,
        "prompt_tokens_max": 166,
        "rep_wall_s": 3.238612665911205,
        "requests_failed": 0,
        "requests_total": 3,
        "success_rate": 0.3333333333333333,
        "task_completion_s": 1.1549684579949826,
        "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": 77.47837505303323,
        "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": 367001600
        },
        "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": 1369194496
        }
      },
      "outcomes": [
        {
          "check_ms": 53.461415925994515,
          "lane": 0,
          "success": false,
          "task_id": "slugify",
          "wall_ms": 651.0395830264315,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 86,
              "decode_ms": 571.288,
              "decode_tokens_per_s": 150.53703210989903,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "slugify#lane0",
              "load_ms": 1.407292,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 15,
              "prompt_eval_ms": 74.318,
              "prompt_tokens": 134,
              "runtime_total_ms": 649.23225,
              "started_at": "2026-10-19T20:53:57.029+00:00",
              "ttft_ms": 79.56087507773191,
              "wall_ms": 650.9269160451367
            }
          ]
        },
        {
          "check_ms": 35.894209053367376,
          "lane": 0,
          "success": true,
          "task_id": "merge_intervals",
          "wall_ms": 1154.9684579949826,
          "failure_category": null,
          "requests": [
            {
              "completion_tokens": 168,
              "decode_ms": 1089.643,
              "decode_tokens_per_s": 154.17893750521958,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "merge_intervals#lane0",
              "load_ms": 1.667125,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 64,
              "prompt_eval_ms": 60.336,
              "prompt_tokens": 157,
              "runtime_total_ms": 1154.023167,
              "started_at": "2026-10-19T20:53:57.734+00:00",
              "ttft_ms": 64.92466700728983,
              "wall_ms": 1154.8578749643639
            }
          ]
        },
        {
          "check_ms": 44.580332934856415,
          "lane": 0,
          "success": false,
          "task_id": "parse_duration",
          "wall_ms": 1249.6509170159698,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 176,
              "decode_ms": 1171.945,
              "decode_tokens_per_s": 150.17769605228915,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "parse_duration#lane0",
              "load_ms": 1.397042,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 64,
              "prompt_eval_ms": 73.102,
              "prompt_tokens": 166,
              "runtime_total_ms": 1248.784542,
              "started_at": "2026-10-19T20:53:58.925+00:00",
              "ttft_ms": 77.47837505303323,
              "wall_ms": 1249.5611250633374
            }
          ]
        }
      ]
    },
    {
      "index": 3,
      "phase": "measured",
      "wall_s": 3.164806249900721,
      "metrics": {
        "aggregate_output_tokens_per_s": 135.86929690039918,
        "decode_tokens_per_s": 154.63009245441108,
        "peak_phys_footprint_bytes": 392167424,
        "peak_rss_bytes": 1396473856,
        "prompt_cached_tokens_total": 143,
        "prompt_eval_ms": 73.277,
        "prompt_tokens_max": 166,
        "rep_wall_s": 3.164806249900721,
        "requests_failed": 0,
        "requests_total": 3,
        "success_rate": 0.3333333333333333,
        "task_completion_s": 1.1578017090214416,
        "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": 77.24620797671378,
        "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": 392167424
        },
        "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": 1396473856
        }
      },
      "outcomes": [
        {
          "check_ms": 39.984832983464,
          "lane": 0,
          "success": false,
          "task_id": "slugify",
          "wall_ms": 638.133459025994,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 86,
              "decode_ms": 556.166,
              "decode_tokens_per_s": 154.63009245441108,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "slugify#lane0",
              "load_ms": 1.766,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 15,
              "prompt_eval_ms": 74.17,
              "prompt_tokens": 134,
              "runtime_total_ms": 634.9065,
              "started_at": "2026-10-19T20:54:00.268+00:00",
              "ttft_ms": 81.66333299595863,
              "wall_ms": 638.0140410037711
            }
          ]
        },
        {
          "check_ms": 31.47695807274431,
          "lane": 0,
          "success": true,
          "task_id": "merge_intervals",
          "wall_ms": 1157.8017090214416,
          "failure_category": null,
          "requests": [
            {
              "completion_tokens": 168,
              "decode_ms": 1093.589,
              "decode_tokens_per_s": 153.6226132486702,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "merge_intervals#lane0",
              "load_ms": 1.478459,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 64,
              "prompt_eval_ms": 59.747,
              "prompt_tokens": 157,
              "runtime_total_ms": 1156.834167,
              "started_at": "2026-10-19T20:54:00.947+00:00",
              "ttft_ms": 63.9384159585461,
              "wall_ms": 1157.7157910214737
            }
          ]
        },
        {
          "check_ms": 38.395625073462725,
          "lane": 0,
          "success": false,
          "task_id": "parse_duration",
          "wall_ms": 1214.168999926187,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 176,
              "decode_ms": 1136.548,
              "decode_tokens_per_s": 154.85487634486182,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "parse_duration#lane0",
              "load_ms": 1.40425,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 64,
              "prompt_eval_ms": 73.277,
              "prompt_tokens": 166,
              "runtime_total_ms": 1213.245041,
              "started_at": "2026-10-19T20:54:02.136+00:00",
              "ttft_ms": 77.24620797671378,
              "wall_ms": 1214.0678750583902
            }
          ]
        }
      ]
    },
    {
      "index": 4,
      "phase": "measured",
      "wall_s": 3.142814167076722,
      "metrics": {
        "aggregate_output_tokens_per_s": 136.8200527108999,
        "decode_tokens_per_s": 154.77950829866916,
        "peak_phys_footprint_bytes": 411041792,
        "peak_rss_bytes": 1415659520,
        "prompt_cached_tokens_total": 143,
        "prompt_eval_ms": 73.761,
        "prompt_tokens_max": 166,
        "rep_wall_s": 3.142814167076722,
        "requests_failed": 0,
        "requests_total": 3,
        "success_rate": 0.3333333333333333,
        "task_completion_s": 1.149120874935761,
        "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": 78.95829202607274,
        "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": 411041792
        },
        "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": 1415659520
        }
      },
      "outcomes": [
        {
          "check_ms": 36.31916700396687,
          "lane": 0,
          "success": false,
          "task_id": "slugify",
          "wall_ms": 635.4447499616072,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 86,
              "decode_ms": 556.085,
              "decode_tokens_per_s": 154.65261605689776,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "slugify#lane0",
              "load_ms": 1.917667,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 15,
              "prompt_eval_ms": 73.761,
              "prompt_tokens": 134,
              "runtime_total_ms": 633.960042,
              "started_at": "2026-10-19T20:54:03.433+00:00",
              "ttft_ms": 79.15674999821931,
              "wall_ms": 635.307333082892
            }
          ]
        },
        {
          "check_ms": 27.16649998910725,
          "lane": 0,
          "success": true,
          "task_id": "merge_intervals",
          "wall_ms": 1149.120874935761,
          "failure_category": null,
          "requests": [
            {
              "completion_tokens": 168,
              "decode_ms": 1085.415,
              "decode_tokens_per_s": 154.77950829866916,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "merge_intervals#lane0",
              "load_ms": 1.349459,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 64,
              "prompt_eval_ms": 59.575,
              "prompt_tokens": 157,
              "runtime_total_ms": 1148.312459,
              "started_at": "2026-10-19T20:54:04.105+00:00",
              "ttft_ms": 63.498707953840494,
              "wall_ms": 1149.0491660078987
            }
          ]
        },
        {
          "check_ms": 38.41104207094759,
          "lane": 0,
          "success": false,
          "task_id": "parse_duration",
          "wall_ms": 1212.0343330316246,
          "failure_category": "checker_failure",
          "requests": [
            {
              "completion_tokens": 176,
              "decode_ms": 1132.778,
              "decode_tokens_per_s": 155.37024906910267,
              "done_reason": "stop",
              "first_chunk_kind": "content",
              "id": "parse_duration#lane0",
              "load_ms": 1.9985,
              "ok": true,
              "origin": "executed",
              "prompt_cached_tokens": 64,
              "prompt_eval_ms": 74.103,
              "prompt_tokens": 166,
              "runtime_total_ms": 1211.112167,
              "started_at": "2026-10-19T20:54:05.281+00:00",
              "ttft_ms": 78.95829202607274,
              "wall_ms": 1211.9279169710353
            }
          ]
        }
      ]
    }
  ],
  "memory_samples": {
    "measured-0": {
      "phys_footprint": [
        [
          0.04,
          298844160
        ],
        [
          2.102,
          314572800
        ],
        [
          3.222,
          314572800
        ]
      ],
      "rss": [
        [
          0.003,
          1285586944
        ],
        [
          0.266,
          1295351808
        ],
        [
          0.528,
          1295319040
        ],
        [
          0.786,
          1303511040
        ],
        [
          1.048,
          1303478272
        ],
        [
          1.311,
          1303494656
        ],
        [
          1.571,
          1303494656
        ],
        [
          1.829,
          1303494656
        ],
        [
          2.087,
          1312800768
        ],
        [
          2.35,
          1312800768
        ],
        [
          2.609,
          1312817152
        ],
        [
          2.873,
          1312817152
        ],
        [
          3.137,
          1312817152
        ],
        [
          3.182,
          1312817152
        ]
      ]
    },
    "measured-1": {
      "phys_footprint": [
        [
          0.04,
          324009984
        ],
        [
          2.108,
          339738624
        ],
        [
          3.223,
          339738624
        ]
      ],
      "rss": [
        [
          0.003,
          1312817152
        ],
        [
          0.262,
          1322614784
        ],
        [
          0.522,
          1322614784
        ],
        [
          0.78,
          1328906240
        ],
        [
          1.043,
          1328906240
        ],
        [
          1.301,
          1328906240
        ],
        [
          1.565,
          1328906240
        ],
        [
          1.828,
          1328906240
        ],
        [
          2.084,
          1338245120
        ],
        [
          2.342,
          1338245120
        ],
        [
          2.6,
          1338245120
        ],
        [
          2.862,
          1338245120
        ],
        [
          3.123,
          1338245120
        ],
        [
          3.183,
          1338245120
        ]
      ]
    },
    "measured-2": {
      "phys_footprint": [
        [
          0.04,
          349175808
        ],
        [
          2.094,
          367001600
        ],
        [
          3.239,
          367001600
        ]
      ],
      "rss": [
        [
          0.003,
          1338245120
        ],
        [
          0.266,
          1349877760
        ],
        [
          0.525,
          1349877760
        ],
        [
          0.782,
          1358053376
        ],
        [
          1.044,
          1358053376
        ],
        [
          1.303,
          1358053376
        ],
        [
          1.567,
          1358053376
        ],
        [
          1.825,
          1358053376
        ],
        [
          2.082,
          1369194496
        ],
        [
          2.344,
          1369194496
        ],
        [
          2.606,
          1369194496
        ],
        [
          2.863,
          1369194496
        ],
        [
          3.126,
          1369194496
        ],
        [
          3.195,
          1369194496
        ]
      ]
    },
    "measured-3": {
      "phys_footprint": [
        [
          0.044,
          374341632
        ],
        [
          2.098,
          392167424
        ],
        [
          3.165,
          392167424
        ]
      ],
      "rss": [
        [
          0.004,
          1369194496
        ],
        [
          0.267,
          1378992128
        ],
        [
          0.526,
          1378992128
        ],
        [
          0.782,
          1387151360
        ],
        [
          1.042,
          1387151360
        ],
        [
          1.303,
          1387151360
        ],
        [
          1.565,
          1387151360
        ],
        [
          1.824,
          1387151360
        ],
        [
          2.083,
          1396473856
        ],
        [
          2.341,
          1396473856
        ],
        [
          2.602,
          1396473856
        ],
        [
          2.861,
          1396473856
        ],
        [
          3.118,
          1396473856
        ],
        [
          3.125,
          1396473856
        ]
      ]
    },
    "measured-4": {
      "phys_footprint": [
        [
          0.047,
          401604608
        ],
        [
          2.101,
          411041792
        ],
        [
          3.143,
          411041792
        ]
      ],
      "rss": [
        [
          0.003,
          1396473856
        ],
        [
          0.264,
          1406320640
        ],
        [
          0.521,
          1406320640
        ],
        [
          0.776,
          1406337024
        ],
        [
          1.039,
          1406337024
        ],
        [
          1.301,
          1406337024
        ],
        [
          1.561,
          1406337024
        ],
        [
          1.821,
          1406337024
        ],
        [
          2.079,
          1415643136
        ],
        [
          2.336,
          1415643136
        ],
        [
          2.597,
          1415659520
        ],
        [
          2.86,
          1415659520
        ],
        [
          3.103,
          1415659520
        ]
      ]
    },
    "warmup--1": {
      "phys_footprint": [
        [
          0.058,
          274726912
        ],
        [
          2.114,
          292552704
        ],
        [
          3.285,
          292552704
        ]
      ],
      "rss": [
        [
          0.004,
          1261043712
        ],
        [
          0.267,
          1265811456
        ],
        [
          0.528,
          1265876992
        ],
        [
          0.785,
          1272446976
        ],
        [
          1.048,
          1274331136
        ],
        [
          1.307,
          1274511360
        ],
        [
          1.569,
          1274527744
        ],
        [
          1.831,
          1274544128
        ],
        [
          2.091,
          1285783552
        ],
        [
          2.353,
          1285767168
        ],
        [
          2.613,
          1285668864
        ],
        [
          2.875,
          1285668864
        ],
        [
          3.134,
          1285586944
        ],
        [
          3.245,
          1285586944
        ]
      ]
    }
  }
}
