Bench / Methodology / run a4223a89-0561-4da7-be16-7552d0ad57e9
Schema-bound extraction
deepseek/deepseek-chat-v3.1 · task v1 · methodology v1 · visitor-key / video-demo
Deterministic check
As of .
Candidate cost: 0.00008221
Judge cost: not recorded
No grand total on this receipt.
Cost source: openrouter_usage
Tokens in / out: 123 / 49
Latency: 1191 ms (wall clock)
Stored at:
Comparison: 7696b7c0-7884-49a9-9ec6-3a230f1ac943
Judge cost not recorded for these runs
Amounts are the exact stored decimal strings. No rounding is applied. candidate_cost_usd is the sum of measured run costs. judge_cost_usd is the sum of stored tier-2 judge ledger rows, or null when none were recorded. total_cost_usd equals candidate plus judge only when every candidate cost is present and a judge cost was recorded.
Derived integrity
These fields are computed from the stored output and evaluation. The output text below is unchanged.
output_incomplete: false
completeness_confidence: high
completeness_reason: —
presentation: scored
Spot check: Human spot check
Spot-check note: Pass: Bright Parcel Co. / 2026-09-03 / total "2500.05" with currency null and po_number null — schema-bound nulls look correct.
Output
{
"vendor": "Bright Parcel Co.",
"invoice_date": "2026-09-03",
"currency": null,
"total": "2500.05",
"po_number": null
}Evaluation stored on this run
{
"tier": 1,
"score": 1,
"tier3": {
"at": "2026-10-02T00:49:53.256Z",
"date": "2026-10-02",
"note": "Pass: Bright Parcel Co. / 2026-09-03 / total \"2500.05\" with currency null and po_number null — schema-bound nulls look correct.",
"passed": true,
"verdict": "agree",
"reviewer": "cos",
"issue_found": false,
"output_read": true
},
"checks": [
{
"type": "json_parse",
"detail": "Output parsed as JSON.",
"passed": true
},
{
"type": "exact_json",
"detail": "Parsed JSON matches the fixture gold.",
"passed": true
}
],
"passed": true,
"status": "scored",
"tier3_kind": "human",
"tier_label": "Deterministic check",
"tier3_label": "Human spot check",
"presentation": "scored",
"score_capped": false,
"display_overall": 1,
"output_incomplete": false,
"completeness_reason": null,
"completeness_confidence": "high"
}