{
  "created_at": "2026-10-26T18:04:00.288805Z",
  "failure": null,
  "partial": false,
  "provenance": {
    "endpoint": {
      "auth_env": "ANVIL_EVALUATION_TOKEN",
      "base_url": "[REDACTED_PRIVATE_VALUE]",
      "model": "llm.evaluation.flare"
    },
    "finished_at": "2026-10-26T18:04:00.288665Z",
    "started_at": "2026-10-26T18:03:15.733859Z",
    "submitted_at": "2026-10-26T16:35:11+00:00",
    "worker": {
      "id": "Primary Node"
    }
  },
  "results": {
    "evidence": {
      "completeness": "completed",
      "created_at": "2026-10-26T18:04:00.278406Z",
      "evidence_kind": "measured",
      "failure": null,
      "identities": {
        "concurrency": {
          "requests": 1,
          "workers": 1
        },
        "context": {
          "advertised_context_tokens": 262144,
          "effective_max_model_len": 262144,
          "observation": "native /v1/models max_model_len"
        },
        "dataset": {
          "name": "deterministic-native",
          "profile_sha256": "fce0e6e1e7497585bdfc6f76507d3baaff99a6b4f174d841d268de20c68de7f6"
        },
        "hardware": {
          "gpu_name": "NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition",
          "gpu_uuids": [
            "[REDACTED_PUBLIC_HARDWARE_ID]"
          ]
        },
        "harnesses": {
          "native": {
            "schema": "anvil-serving.context/v1"
          }
        },
        "image": {
          "id": "sha256:67124437a73011d63c2b25c939b9c48581eba90e51c6e565d4c808d161d10fc6",
          "reference": "ghcr.io/local-inference-lab/flare:release-2193455-k7-pf4096-20261022@sha256:67124437a73011d63c2b25c939b9c48581eba90e51c6e565d4c808d161d10fc6"
        },
        "model": {
          "repository": "local-inference-lab/Qwen3.8-Flash-Next-FLARE",
          "revision": "431b302155d53e296aa51633a997b4b5fd92e751"
        },
        "runtime": {
          "benchmark_source_revision": "a5ccb7454ad49f47e5a953b130696fff69cdb829",
          "engine": "flare-2193455651794642",
          "operator_provenance": {
            "source_commit": "c87dc0ac4f5399b3cb5da17d9cf8babafaf2e143",
            "source_tree": "4e35fc3ecd99d97abf8fd3a297fe7583f7c51b53",
            "tree_identical_to_main_commit": "d6997162330f41593663fbf9f9ebe0618ebb9ad8"
          },
          "recipe_sha256": "6fd91446e710888c9bf9a71a2a52b2d38ba65634110134f02398c3143c2513fa",
          "request_overrides": {
            "temperature": 0.6,
            "top_p": 0.95
          },
          "sampling_defaults_observed": {
            "temperature": 1.0,
            "top_k": 20,
            "top_p": 0.949999988079071
          },
          "source_revision": "2193455651794642debdaad0dda91e77ab675031",
          "stored_data_verification": {
            "evidence": "startup reported Stored data: Not checked (--verify-weights to check)",
            "full_payload_verified": false,
            "status": "not_checked"
          },
          "unspecified_sampling_controls_equivalence": "not_asserted"
        },
        "served_model": {
          "configured_context_tokens": 262144,
          "id": "qwen38-flash-next-flare-tp1-c16-mtp5",
          "router_alias": "llm.evaluation.flare"
        },
        "topology": {
          "client_topology": "co-resident",
          "gpu_uuids": [
            "[REDACTED_PUBLIC_HARDWARE_ID]"
          ],
          "max_concurrency": 16,
          "model_host_id": "Primary Node",
          "mtp_draft_tokens": 5,
          "tensor_parallel": 1
        }
      },
      "promotion": {
        "authorized": false,
        "message": "Benchmark evidence does not authorize model promotion; promotion is a separate human decision."
      },
      "run": {
        "ownership_id": "evaluation-platform",
        "profile": "scout",
        "run_id": "flare-r2-context-scout-r1-20261026",
        "spec_sha256": "55ea89c72809b3807309abbb8136a484b0eb858cb5750a43deab8cbfff709dcd",
        "suite": "context"
      },
      "schema": "anvil-serving.benchmark-evidence/v1",
      "stages": [
        {
          "evidence": [
            {
              "bytes": 586,
              "path": "[REDACTED_PRIVATE_VALUE]",
              "sha256": "222f01174f27b930ef319b13fd3c14cfa618f025237bcdbbff3ad4f552cdc046"
            }
          ],
          "name": "asset_preparation",
          "sequence": 0,
          "status": "completed"
        },
        {
          "evidence": [
            {
              "bytes": 2211,
              "path": "[REDACTED_PRIVATE_VALUE]",
              "sha256": "01b46b2f9da797a256a40ca136034f27cae439b1c38299943f7d9878e9f8dbd7"
            }
          ],
          "name": "preflight",
          "sequence": 1,
          "status": "completed"
        },
        {
          "evidence": [
            {
              "bytes": 28554,
              "path": "[REDACTED_PRIVATE_VALUE]",
              "sha256": "c148f12c28566177265cbb2307824afd6dd449a44efe1f1a954552005fd5dcf0"
            }
          ],
          "name": "context",
          "sequence": 2,
          "status": "completed"
        }
      ],
      "summary": {
        "advertised_context": 262144,
        "attempted_buckets": [
          8192,
          32768,
          114688
        ],
        "buckets": [
          {
            "completed_count": 3,
            "completion_rate": 1.0,
            "engine_telemetry": {
              "available": false,
              "observations": []
            },
            "failures": {},
            "latency_ms": {
              "available": true,
              "mean": 1334.2305682599545,
              "observations": [
                1262.2330028098077,
                1425.6107779219747,
                1314.847924048081
              ]
            },
            "meets_policy": true,
            "pass_rate": 1.0,
            "passed_count": 3,
            "relative_drop_from_baseline": 0.0,
            "requested_tokens": 8192,
            "sample_count": 3,
            "samples": [
              {
                "answer_sha256": "165c06e1078f0d23d51237f55fdf201897c11ab1ba6b89b4be0058e8551485db",
                "case_id": "native-needle-8192-0.500-r0",
                "case_type": "native-needle",
                "completed": true,
                "distractor_count": 0,
                "engine_telemetry": null,
                "failure": null,
                "finish_reason": "stop",
                "latency_ms": 1262.2330028098077,
                "passed": true,
                "position": 0.5,
                "prompt_tokens": 8198,
                "raw_reasoning": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "raw_reasoning_field": "reasoning_content",
                "raw_reasoning_truncated": false,
                "requested_tokens": 8192,
                "schema": "anvil-serving.context-observation/v1",
                "target_count": 1,
                "throughput_tps": 97.44635081335578,
                "token_measurement": "usage",
                "visible_answer": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "visible_answer_truncated": false
              },
              {
                "answer_sha256": "ea77d2c40d5ae22b614345bf65faaf4a798b6926e2753eaa34d64261ffa8f4cb",
                "case_id": "native-order-8192-0.500-r0",
                "case_type": "native-order",
                "completed": true,
                "distractor_count": 0,
                "engine_telemetry": null,
                "failure": null,
                "finish_reason": "stop",
                "latency_ms": 1425.6107779219747,
                "passed": true,
                "position": 0.5,
                "prompt_tokens": 8202,
                "raw_reasoning": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "raw_reasoning_field": "reasoning_content",
                "raw_reasoning_truncated": false,
                "requested_tokens": 8192,
                "schema": "anvil-serving.context-observation/v1",
                "target_count": 3,
                "throughput_tps": 140.29074632244834,
                "token_measurement": "usage",
                "visible_answer": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "visible_answer_truncated": false
              },
              {
                "answer_sha256": "165c06e1078f0d23d51237f55fdf201897c11ab1ba6b89b4be0058e8551485db",
                "case_id": "native-distractor-8192-0.500-r0",
                "case_type": "native-distractor",
                "completed": true,
                "distractor_count": 2,
                "engine_telemetry": null,
                "failure": null,
                "finish_reason": "stop",
                "latency_ms": 1314.847924048081,
                "passed": true,
                "position": 0.5,
                "prompt_tokens": 8208,
                "raw_reasoning": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "raw_reasoning_field": "reasoning_content",
                "raw_reasoning_truncated": false,
                "requested_tokens": 8192,
                "schema": "anvil-serving.context-observation/v1",
                "target_count": 1,
                "throughput_tps": 113.32109004763612,
                "token_measurement": "usage",
                "visible_answer": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "visible_answer_truncated": false
              }
            ],
            "throughput_tps": {
              "available": true,
              "mean": 117.0193957278134,
              "observations": [
                97.44635081335578,
                140.29074632244834,
                113.32109004763612
              ]
            }
          },
          {
            "completed_count": 3,
            "completion_rate": 1.0,
            "engine_telemetry": {
              "available": false,
              "observations": []
            },
            "failures": {},
            "latency_ms": {
              "available": true,
              "mean": 3233.0056069574007,
              "observations": [
                3365.8726499415934,
                3260.27259696275,
                3072.871573967859
              ]
            },
            "meets_policy": true,
            "pass_rate": 1.0,
            "passed_count": 3,
            "relative_drop_from_baseline": 0.0,
            "requested_tokens": 32768,
            "sample_count": 3,
            "samples": [
              {
                "answer_sha256": "165c06e1078f0d23d51237f55fdf201897c11ab1ba6b89b4be0058e8551485db",
                "case_id": "native-needle-32768-0.500-r0",
                "case_type": "native-needle",
                "completed": true,
                "distractor_count": 0,
                "engine_telemetry": null,
                "failure": null,
                "finish_reason": "stop",
                "latency_ms": 3365.8726499415934,
                "passed": true,
                "position": 0.5,
                "prompt_tokens": 32658,
                "raw_reasoning": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "raw_reasoning_field": "reasoning_content",
                "raw_reasoning_truncated": false,
                "requested_tokens": 32768,
                "schema": "anvil-serving.context-observation/v1",
                "target_count": 1,
                "throughput_tps": 37.43457138884516,
                "token_measurement": "usage",
                "visible_answer": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "visible_answer_truncated": false
              },
              {
                "answer_sha256": "ea77d2c40d5ae22b614345bf65faaf4a798b6926e2753eaa34d64261ffa8f4cb",
                "case_id": "native-order-32768-0.500-r0",
                "case_type": "native-order",
                "completed": true,
                "distractor_count": 0,
                "engine_telemetry": null,
                "failure": null,
                "finish_reason": "stop",
                "latency_ms": 3260.27259696275,
                "passed": true,
                "position": 0.5,
                "prompt_tokens": 32662,
                "raw_reasoning": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "raw_reasoning_field": "reasoning_content",
                "raw_reasoning_truncated": false,
                "requested_tokens": 32768,
                "schema": "anvil-serving.context-observation/v1",
                "target_count": 3,
                "throughput_tps": 41.40758049672447,
                "token_measurement": "usage",
                "visible_answer": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "visible_answer_truncated": false
              },
              {
                "answer_sha256": "165c06e1078f0d23d51237f55fdf201897c11ab1ba6b89b4be0058e8551485db",
                "case_id": "native-distractor-32768-0.500-r0",
                "case_type": "native-distractor",
                "completed": true,
                "distractor_count": 2,
                "engine_telemetry": null,
                "failure": null,
                "finish_reason": "stop",
                "latency_ms": 3072.871573967859,
                "passed": true,
                "position": 0.5,
                "prompt_tokens": 32668,
                "raw_reasoning": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "raw_reasoning_field": "reasoning_content",
                "raw_reasoning_truncated": false,
                "requested_tokens": 32768,
                "schema": "anvil-serving.context-observation/v1",
                "target_count": 1,
                "throughput_tps": 44.2582765749593,
                "token_measurement": "usage",
                "visible_answer": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "visible_answer_truncated": false
              }
            ],
            "throughput_tps": {
              "available": true,
              "mean": 41.03347615350964,
              "observations": [
                37.43457138884516,
                41.40758049672447,
                44.2582765749593
              ]
            }
          },
          {
            "completed_count": 3,
            "completion_rate": 1.0,
            "engine_telemetry": {
              "available": false,
              "observations": []
            },
            "failures": {},
            "latency_ms": {
              "available": true,
              "mean": 9930.724741891026,
              "observations": [
                9627.12616682984,
                10059.630764881149,
                10105.417293962091
              ]
            },
            "meets_policy": true,
            "pass_rate": 1.0,
            "passed_count": 3,
            "relative_drop_from_baseline": 0.0,
            "requested_tokens": 114688,
            "sample_count": 3,
            "samples": [
              {
                "answer_sha256": "165c06e1078f0d23d51237f55fdf201897c11ab1ba6b89b4be0058e8551485db",
                "case_id": "native-needle-114688-0.500-r0",
                "case_type": "native-needle",
                "completed": true,
                "distractor_count": 0,
                "engine_telemetry": null,
                "failure": null,
                "finish_reason": "stop",
                "latency_ms": 9627.12616682984,
                "passed": true,
                "position": 0.5,
                "prompt_tokens": 114578,
                "raw_reasoning": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "raw_reasoning_field": "reasoning_content",
                "raw_reasoning_truncated": false,
                "requested_tokens": 114688,
                "schema": "anvil-serving.context-observation/v1",
                "target_count": 1,
                "throughput_tps": 14.646115315888764,
                "token_measurement": "usage",
                "visible_answer": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "visible_answer_truncated": false
              },
              {
                "answer_sha256": "ea77d2c40d5ae22b614345bf65faaf4a798b6926e2753eaa34d64261ffa8f4cb",
                "case_id": "native-order-114688-0.500-r0",
                "case_type": "native-order",
                "completed": true,
                "distractor_count": 0,
                "engine_telemetry": null,
                "failure": null,
                "finish_reason": "stop",
                "latency_ms": 10059.630764881149,
                "passed": true,
                "position": 0.5,
                "prompt_tokens": 114582,
                "raw_reasoning": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "raw_reasoning_field": "reasoning_content",
                "raw_reasoning_truncated": false,
                "requested_tokens": 114688,
                "schema": "anvil-serving.context-observation/v1",
                "target_count": 3,
                "throughput_tps": 21.869589962291148,
                "token_measurement": "usage",
                "visible_answer": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "visible_answer_truncated": false
              },
              {
                "answer_sha256": "165c06e1078f0d23d51237f55fdf201897c11ab1ba6b89b4be0058e8551485db",
                "case_id": "native-distractor-114688-0.500-r0",
                "case_type": "native-distractor",
                "completed": true,
                "distractor_count": 2,
                "engine_telemetry": null,
                "failure": null,
                "finish_reason": "stop",
                "latency_ms": 10105.417293962091,
                "passed": true,
                "position": 0.5,
                "prompt_tokens": 114588,
                "raw_reasoning": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "raw_reasoning_field": "reasoning_content",
                "raw_reasoning_truncated": false,
                "requested_tokens": 114688,
                "schema": "anvil-serving.context-observation/v1",
                "target_count": 1,
                "throughput_tps": 17.41640101346024,
                "token_measurement": "usage",
                "visible_answer": "[REDACTED_PUBLIC_RESPONSE_TEXT]",
                "visible_answer_truncated": false
              }
            ],
            "throughput_tps": {
              "available": true,
              "mean": 17.97736876388005,
              "observations": [
                14.646115315888764,
                21.869589962291148,
                17.41640101346024
              ]
            }
          }
        ],
        "effective_context": 114688,
        "first_material_degradation": null,
        "notes": [
          "effective_context uses attempted buckets only",
          "missing engine telemetry is unavailable and is not inferred from latency"
        ],
        "schema": "anvil-serving.context-curve/v1",
        "threshold_policy": {
          "baseline_bucket": 8192,
          "baseline_pass_rate": 1.0,
          "max_relative_drop": 0.25,
          "pass_rate_floor": 0.75
        }
      }
    }
  },
  "run": {
    "ownership_id": "evaluation-platform",
    "profile": "scout",
    "run_id": "flare-r2-context-scout-r1-20261026",
    "spec_sha256": "55ea89c72809b3807309abbb8136a484b0eb858cb5750a43deab8cbfff709dcd",
    "suite": "context"
  },
  "schema": "anvil-serving.benchmark-result/v1",
  "status": "completed"
}
