Off-road Mud Game — GPT-5.6 Luna Max

Measured harness ledgerPublic result

Off-road Mud Game — GPT-5.6 Luna Max

Build a one-request procedural off-road driving game with vehicle physics, independent suspension, streamed terrain, mud feedback, and multiple cameras.

Max reasoningHeadline result

Workflow cost: $0.73
Wall-clock: 51m 53.5s wall-clock
Processed tokens: 25.51M processed
Record state: partial_token_timing_source_build_ledger

Public summary

GPT-5.6 Luna Max partial_token_timing_source_build_ledger ledger: 51m 53.5s wall-clock, 25.51M processed, and $0.73 Token-only Standard API-equivalent estimate, re-priced at the official GPT-5.6 Luna rates verified during archival; not the actual Codex subscription charge..

Run identity and stack

Result ID: off-road-driving-game-threejs-gpt-5.6-luna-max
Technical model: gpt-5.6-luna
Provider: OpenAI Codex
Stack: OpenAI Codex
Stack: Technical model/configuration: gpt-5.6-luna
Stack: Three.js vehicle workflow
Stack: Harness v1 off-road prompt

Cost basis

The official Luna model page applies long-context rates only when a call exceeds 272,000 input tokens. The receipt reports zero such calls.
The submitted receipt used five-times-higher rates than the official GPT-5.6 Luna model page. Its tokens are retained but its cost is re-priced above.

Primary artifact integrity

Kind: ledger-checksummed-source-file
Path: artifacts/off-road-driving-game-threejs-gpt-5.6-luna-max/source/src/main.js
SHA-256: 9d328fefcab954cc44abee962dab04c6577765add39a1b290c0954d8739921dc

Recorded caveats

Wall-clock is end-to-end workflow latency, including tools and idle gaps; it is not model-only compute time.
The post-generation metrics request is included in the recorded wall-clock and token total.
Output tokens include hidden reasoning, visible prose/code, and tool-call JSON.
Cache-read tokens are discounted, so total processed tokens substantially overstate cost.
The archive contains a production build created during archival verification, not a recorded final gameplay capture.
No independent browser acceptance, sustained-drive, local-FPS, generation-seam, suspension-articulation, or blind-evaluation receipt is archived.

Visible evidence gaps

independent browser acceptance run
local FPS, browser, viewport, and hardware receipt
multi-minute sustained-drive and generation-seam receipt
four-corner suspension-articulation receipt
final gameplay capture
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.

Browse Builder Return to GPT-5.6 Luna