{
  "schema_version": "remakebench.public-evidence.v1",
  "snapshot": {
    "benchmark_id": "tech-review-001",
    "benchmark_version": "v1",
    "immutable": true
  },
  "result_id": "space-flight-game-gpt-5.6-luna-xhigh",
  "task": {
    "id": "space-flight-game-threejs",
    "title": "Three.js explorable star-system flight game",
    "benchmark_prompt_version": "v1"
  },
  "configuration": {
    "id": "luna-xhigh",
    "model": "gpt-5.6-luna",
    "reasoning": "xhigh",
    "provider_agent": "OpenAI Codex"
  },
  "status": "partial_token_timing_and_source_ledger",
  "measurements": {
    "wall_clock_seconds": 655.9,
    "wall_clock_display": "10:55.9",
    "total_processed_tokens": 1201708,
    "reported_cost_usd": 0.33
  },
  "cost_provenance": {
    "currency": "USD",
    "reported_total_basis": "per-ledger rounded total",
    "calculation_location": "api_cost.total_usd",
    "calculated_total_usd": 0.3285488,
    "estimate_type": "API-equivalent estimate, not a subscription invoice",
    "pricing_basis": null,
    "pricing_mode": null,
    "cache_write_assumption": null,
    "verified_live_pricing": true,
    "pricing_accessed_on": "2026-07-12T05:56:22Z",
    "pricing_sources": [
      "https://developers.openai.com/api/docs/models/gpt-5.6-luna",
      "https://developers.openai.com/api/docs/pricing"
    ]
  },
  "primary_artifact": {
    "kind": "threejs-space-flight-game-primary-source",
    "sha256": "a5badbbaf62208d01644f8213313da39653d6021d9699e58617c6ced14d7e1f9"
  },
  "public_standardized_captures": [],
  "caveats": [
    "Wall-clock is end-to-end latency, not model-only compute; it includes tool time and idle gaps between user turns.",
    "Output tokens include hidden reasoning, visible prose/code, and tool-call JSON.",
    "Cached input is deeply discounted, so total processed tokens overstate cost.",
    "This is an API-equivalent estimate rather than the actual charge for a subscription-backed Codex session.",
    "Separately priced tools and non-token services are excluded.",
    "Cache-creation tokens are zero because the Codex transcript schema does not expose a cache-write field.",
    "Subagent logs are excluded to avoid double-counting inherited parent context."
  ],
  "missing_evidence": [
    "browser and hardware environment",
    "local FPS",
    "final capture",
    "blind-evaluation record"
  ],
  "source_provenance": {
    "harness_commit": "3f14507a8ce536d68a1f472f34f4c1a64c511f82",
    "source_record_sha256": "3e538987d2b46706dae91bd17454d3968adc47532af9d4c200b7aba53b74e649",
    "primary_artifact_sha256_verified_at_source_commit": true
  }
}