{
  "passed": true,
  "checks": {
    "completed": true,
    "unique_frozen_case_ids": true,
    "frozen_cases_hash": true,
    "expected_models_present": true,
    "frozen_source_code_hashes": true,
    "plan_count": true,
    "plan_sha256": true,
    "seeded_plan_reproduces": true,
    "unique_attempt_identities": true,
    "every_record_matches_contract_and_source": true,
    "complete_quality_cross_product": true,
    "attempts.jsonl_unique_dispatches": true,
    "attempts.jsonl_frozen_request_hashes": true,
    "saved_exact_requests_hash": true,
    "metadata_billing_complete_or_unknown": true,
    "named_source_hashes_match": true,
    "current_code_matches_saved_snapshot": true
  },
  "issues": [],
  "issue_count": 0,
  "run_dir": "benchmark/multimodel/runs/quality-20261002T160544592288Z",
  "raw_sha256": "9b949a90dcc900c2228ef035987ae306a858c138eab153eb7cf4bb6056357a22",
  "case_sha256": "e271790b2ee38a1c231e312fa15ece2a56c95f6bf705294f1637d43b2edcf256",
  "attempts": 14355,
  "valid": 14351,
  "cost": {
    "requests": 14355,
    "known_billed_usd": 1.3245464012,
    "observed_bills": 14351,
    "missing_bills": 4,
    "total_billed_usd": null,
    "usd_per_1000_attempts": null
  },
  "observed_usage": {
    "DeepSeek V4.1 Flash": {
      "valid_calls": 4785,
      "output_tokens": {
        "observed": 4785,
        "min": 12,
        "max": 21,
        "total": 71528
      },
      "reasoning_counter_observed": 4785,
      "reasoning_counter_unknown": 0,
      "reasoning_tokens_reported_total": 0,
      "visible_reasoning_calls": 0,
      "cache_read_counter_observed": 4785,
      "cache_write_counter_observed": 4785
    },
    "Hy4 Preview": {
      "valid_calls": 4781,
      "output_tokens": {
        "observed": 4781,
        "min": 12,
        "max": 19,
        "total": 76770
      },
      "reasoning_counter_observed": 4781,
      "reasoning_counter_unknown": 0,
      "reasoning_tokens_reported_total": 0,
      "visible_reasoning_calls": 0,
      "cache_read_counter_observed": 4781,
      "cache_write_counter_observed": 4781
    },
    "MiMo V2.6 Flash": {
      "valid_calls": 4785,
      "output_tokens": {
        "observed": 4785,
        "min": 12,
        "max": 23,
        "total": 81649
      },
      "reasoning_counter_observed": 4785,
      "reasoning_counter_unknown": 0,
      "reasoning_tokens_reported_total": 0,
      "visible_reasoning_calls": 0,
      "cache_read_counter_observed": 4785,
      "cache_write_counter_observed": 4785
    }
  },
  "exact_payload_factory_supplied": true,
  "seeded_plan_factory_supplied": true,
  "limitations": [
    "Missing reasoning/cache counters are unobserved, not verified zero. Without factories, quality/timing source content and contracts are checked, but complete payload and seeded plan regeneration are not established."
  ],
  "generated_at_utc": "2026-10-02T16:42:48.067168+00:00"
}