{
  "directive": "Do not name a winner: the confidence intervals overlap. Report the range, the n and the observation date.",
  "objective_and_population": "Faithfully transcribe audio into text (speech-to-text via API) measured on FLEURS dev fr_fr/de_de/en_us, read speech, encyclopedic domain; France/Germany/USA accents (90 frozen units), observed 2026-09-02T18:42:22.745775Z.",
  "attribution": "TORNEO. CC-BY-4.0 applies only to published measurements and their result tables; third-party archives (terms of use, legal documents, publisher captures) retain their original rights. Licensing does not establish publication or scientific validity.",
  "blocks_replicated": 2,
  "category": "transcription",
  "citation": "TORNEO, run TRANSCRIPTION-001, observed 2026-09-02T18:42:22.745775Z, status OK: Faithfully transcribe audio into text (speech-to-text via API) measured on FLEURS dev fr_fr/de_de/en_us, read speech, encyclopedic domain; France/Germany/USA accents (90 frozen units), observed 2026-09-02T18:42:22.745775Z. https://torneo.ai/runs/TRANSCRIPTION-001/result.json",
  "conflicts": [
    "gemini-3-5-transcribe: devlo is a paying customer of Google, the vendor of this arm, billed per call; devlo is a user of the tool, not a vendor; same conditions and same protocol as any customer, journaled; what this run cost is in FUNDING.json (CONFLICT_REGISTER.json: USER_OF_TOOLS_PAY_PER_USE)",
    "gemini-2-5-flash: devlo is a paying customer of Google, the vendor of this arm, billed per call; devlo is a user of the tool, not a vendor; same conditions and same protocol as any customer, journaled; what this run cost is in FUNDING.json (CONFLICT_REGISTER.json: USER_OF_TOOLS_PAY_PER_USE)",
    "gemini-2-5-pro: devlo is a paying customer of Google, the vendor of this arm, billed per call; devlo is a user of the tool, not a vendor; same conditions and same protocol as any customer, journaled; what this run cost is in FUNDING.json (CONFLICT_REGISTER.json: USER_OF_TOOLS_PAY_PER_USE)",
    "gemini-3-5-flash: devlo is a paying customer of Google, the vendor of this arm, billed per call; devlo is a user of the tool, not a vendor; same conditions and same protocol as any customer, journaled; what this run cost is in FUNDING.json (CONFLICT_REGISTER.json: USER_OF_TOOLS_PAY_PER_USE)"
  ],
  "context": "FLEURS dev fr_fr/de_de/en_us, read speech, encyclopedic domain; France/Germany/USA accents; NO Swiss accents and no B2B register in this run",
  "evidence_uri": "runs/TRANSCRIPTION-001",
  "funding": "fonds propres devlo",
  "license": "CC-BY-4.0",
  "limits": [
    "Swiss accents and B2B register are not covered by this run (no open corpus available; phase 2).",
    "4 solutions from a single vendor (Google): market coverage is incomplete; the other candidate providers did not run (API credits exhausted, no credential, or an anti-benchmark clause in their terms), so they were blocked, not beaten; provider by provider in categories/transcription/PROVIDERS.json and legal/.",
    "tnorm.v1 does not normalize numbers.",
    "Wall-clock latency depends on the runner's network.",
    "Canonical metric = share of clips transcribed perfectly (tnorm.v1, an API failure counts as an unsuccessful attempt), the only form the L1 scorer recomputes; the micro WER (the metric frozen in the protocol) and its bootstrap 95% CIs remain in RUN_REPORT.json, reproducible from events.l2stub.ndjson (amendment A1)."
  ],
  "metric": "perfect_transcription_rate",
  "metric_plain_label": "Share of recordings transcribed with no error at all",
  "observed_at": "2026-09-02T18:42:22.745775Z",
  "participants": [
    {
      "name": "gemini-3-5-transcribe",
      "vendor": "Google",
      "outcome": {
        "estimate": 0.522222,
        "interval": {
          "low": 0.420246,
          "high": 0.622379,
          "confidence": 0.95,
          "method": "wilson"
        },
        "n": 90,
        "successes": 47,
        "unit": "perfect_transcription_rate"
      },
      "blocks_observed": 2,
      "cost": {
        "total_usd": 0.043494,
        "per_unit_usd": 0.000925,
        "unit": "perfect_transcription_rate"
      },
      "latency": {
        "p50_ms": 1481.0,
        "p95_ms": 1913.0
      },
      "reliability": {
        "error_rate": 0.155556,
        "incidents": 14
      },
      "access": {
        "api": true,
        "cli": false,
        "mcp": false,
        "auth": "api_key"
      },
      "status": "OK",
      "rank": {
        "best": 1,
        "worst": 4
      }
    },
    {
      "name": "gemini-2-5-flash",
      "vendor": "Google",
      "outcome": {
        "estimate": 0.566667,
        "interval": {
          "low": 0.463641,
          "high": 0.664234,
          "confidence": 0.95,
          "method": "wilson"
        },
        "n": 90,
        "successes": 51,
        "unit": "perfect_transcription_rate"
      },
      "blocks_observed": 2,
      "cost": {
        "total_usd": 0.046157,
        "per_unit_usd": 0.000905,
        "unit": "perfect_transcription_rate"
      },
      "latency": {
        "p50_ms": 1533.0,
        "p95_ms": 2160.0
      },
      "reliability": {
        "error_rate": 0.0,
        "incidents": 0
      },
      "access": {
        "api": true,
        "cli": false,
        "mcp": false,
        "auth": "api_key"
      },
      "status": "OK",
      "rank": {
        "best": 1,
        "worst": 4
      }
    },
    {
      "name": "gemini-2-5-pro",
      "vendor": "Google",
      "outcome": {
        "estimate": 0.611111,
        "interval": {
          "low": 0.507825,
          "high": 0.705301,
          "confidence": 0.95,
          "method": "wilson"
        },
        "n": 90,
        "successes": 55,
        "unit": "perfect_transcription_rate"
      },
      "blocks_observed": 2,
      "cost": {
        "total_usd": 0.206655,
        "per_unit_usd": 0.003757,
        "unit": "perfect_transcription_rate"
      },
      "latency": {
        "p50_ms": 3385.0,
        "p95_ms": 6092.0
      },
      "reliability": {
        "error_rate": 0.0,
        "incidents": 0
      },
      "access": {
        "api": true,
        "cli": false,
        "mcp": false,
        "auth": "api_key"
      },
      "status": "OK",
      "rank": {
        "best": 1,
        "worst": 4
      }
    },
    {
      "name": "gemini-3-5-flash",
      "vendor": "Google",
      "outcome": {
        "estimate": 0.644444,
        "interval": {
          "low": 0.541502,
          "high": 0.735561,
          "confidence": 0.95,
          "method": "wilson"
        },
        "n": 90,
        "successes": 58,
        "unit": "perfect_transcription_rate"
      },
      "blocks_observed": 2,
      "cost": {
        "total_usd": 0.280255,
        "per_unit_usd": 0.004832,
        "unit": "perfect_transcription_rate"
      },
      "latency": {
        "p50_ms": 2306.0,
        "p95_ms": 4177.0
      },
      "reliability": {
        "error_rate": 0.0,
        "incidents": 0
      },
      "access": {
        "api": true,
        "cli": false,
        "mcp": false,
        "auth": "api_key"
      },
      "status": "OK",
      "rank": {
        "best": 1,
        "worst": 4
      }
    }
  ],
  "population": {
    "description": "FLEURS dev fr_fr/de_de/en_us, read speech, encyclopedic domain; France/Germany/USA accents",
    "size": 90,
    "frozen_at": "2026-09-02T16:46:00Z",
    "contains_personal_data": false
  },
  "promise": "Faithfully transcribe audio into text (speech-to-text via API)",
  "protocol_lock_sha256": "7056f0e2f8d0d81ca2c9c040b2a065a71256d94e9ec47b0d675a628f898301f6",
  "protocol_version": "1.0",
  "raw_data_sha256": "9e870988ea9e0979f0df49f07a1fc10a09f58d13621b67b99b50207cc5611db7",
  "reproduce_cmd": "gladiator reproduce runs/TRANSCRIPTION-001",
  "result_sha256": "e6377e76fecdfab6861603a59eec800e0c9cbf27324d59a96396dd79cab0720c",
  "run_id": "TRANSCRIPTION-001",
  "runner": "devlo lane L2 (agent)",
  "schema_version": "result.v1",
  "status": "OK",
  "superseded_by": null,
  "task": "Batch transcription of FR/DE/EN clips of 5 to 30 s, language hint provided, plain-text output",
  "valid_until": "2026-12-01T18:42:22Z"
}