{
  "schema_version": "remakebench.public-evidence.v1",
  "snapshot": {
    "benchmark_id": "tech-review-001",
    "benchmark_version": "v1",
    "immutable": true
  },
  "result_id": "oasis-outpost-gpt-5.6-sol-ultra",
  "task": {
    "id": "oasis-outpost-blender-mcp",
    "title": "Oasis Outpost voxel diorama",
    "benchmark_prompt_version": "v1"
  },
  "configuration": {
    "id": "sol-ultra",
    "model": "gpt-5.6-sol",
    "reasoning": "Ultra",
    "provider_agent": "OpenAI Codex"
  },
  "status": "partial_token_timing_and_artifact_ledger",
  "measurements": {
    "wall_clock_seconds": 990.9,
    "wall_clock_display": "16:30.9",
    "total_processed_tokens": 1850193,
    "reported_cost_usd": 5.51
  },
  "cost_provenance": {
    "currency": "USD",
    "reported_total_basis": "per-ledger rounded total",
    "calculation_location": "api_cost.total_usd",
    "calculated_total_usd": 5.512508,
    "estimate_type": "API-equivalent estimate, not a subscription invoice",
    "pricing_basis": "Priority API short-context rates as an API-equivalent scenario because the supplied transcript observed service_tier=priority; this is not proof of an API invoice.",
    "pricing_mode": null,
    "cache_write_assumption": null,
    "verified_live_pricing": true,
    "pricing_accessed_on": "2026-07-13T01:32:19Z",
    "pricing_sources": [
      "https://developers.openai.com/api/docs/models/gpt-5.6-sol",
      "https://developers.openai.com/api/docs/pricing"
    ]
  },
  "primary_artifact": {
    "kind": "blender-scene",
    "sha256": "4192f7876576ce27ebfba03a2b5fdc6e7258e338df468e43b127f6c595e3c137"
  },
  "public_standardized_captures": [
    {
      "kind": "poster",
      "url": "/harness/blender/oasis-outpost/p2v6/poster.webp"
    },
    {
      "kind": "video",
      "url": "/harness/blender/oasis-outpost/p2v6/turntable.mp4"
    }
  ],
  "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.",
    "The supplied record observed Priority service tier, so this estimate uses Priority rates and is not directly price-comparable with Standard-tier estimates.",
    "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": [
    "Blender and render environment",
    "final capture metadata",
    "blind-evaluation record"
  ],
  "source_provenance": {
    "harness_commit": "3f14507a8ce536d68a1f472f34f4c1a64c511f82",
    "source_record_sha256": "2094beb1017922f1f0da8ead24d7c510a3d2a75ba28cabd87d0bd29052daed93",
    "primary_artifact_sha256_verified_at_source_commit": true
  }
}