Measured harness ledgerPublic result
GPT-6 AstraJRPG boss battle — GPT-6 Astra Max
Build an interactive Three.js JRPG boss battle with supplied character assets, required combat beats, animation, sound controls, effects, and a validator-ready game loop.
Max reasoningHeadline result
- Workflow cost
- $12.65
- Wall-clock
- 34m 22s wall-clock
- Processed tokens
- 7.39M processed
- Record state
- partial_completed_run_metrics_with_live_operator_smoke
Public summary
GPT-6 Astra Max partial_completed_run_metrics_with_live_operator_smoke ledger: 34m 22s wall-clock, 7.39M processed, and $12.65 API-equivalent estimate, not a subscription invoice.
Run identity and stack
- Result ID: jrpg-boss-battle-gpt-6-astra-max
- Technical model: gpt-6-astra
- Provider: OpenAI Codex
- Stack: OpenAI Codex
- Stack: Technical model/configuration: gpt-6-astra
- Stack: Three.js / Vite game
- Stack: Supplied GLB fixture bundle
- Stack: Harness v1 JRPG validator
Primary artifact integrity
- Kind: interactive-threejs-jrpg-boss-battle
- Path: artifacts/jrpg-boss-battle-gpt-6-astra-max/source/src/main.js
- SHA-256: 5212ab3044796c01ea68478ed4caf4ed7ca2beb5b3e250d62c7a6145f1d9cbaa
Recorded caveats
- Wall-clock is end-to-end workflow latency, not model-only compute.
- Output tokens include hidden reasoning, code, and tool-call JSON.
- Cache reads are discounted, so processed-token volume overstates cost.
- The public metrics projection is hash-bound to a private raw receipt because that receipt contains local transcript paths and session identifiers.
- The independent smoke checked only the sound-off victory path; it does not establish the claimed validator score, local FPS, sound-on path, defeat path, or blind visual quality.
Visible evidence gaps
- retained validator scorecard and capture from this run
- independent full validator replay including sound-on and defeat paths
- local FPS and environment identity
- blind-evaluation record
Public result only
This result keeps its public summary and evidence, but it does not currently have a matching Builder test with prompts, projects, Harness workflows or skills.