Measured harness ledgerPublic result
Grok 4.7Space Flight Stage 2 — Landfall — Grok 4.7 xhigh
Extend the Stage 1 space-flight project with a seamless orbit-to-surface round trip, explorable terrain, takeoff, landing, and a fixed character asset using one frozen follow-on request.
xhigh reasoningHeadline result
- Workflow cost
- $5.83
- Wall-clock
- Not recorded
- Processed tokens
- Not recorded
- Record state
- complete_model_internal_judge_passed
Public summary
Grok 4.7 xhigh complete_model_internal_judge_passed ledger: Not recorded wall-clock, Not recorded, and $5.83 Provider-recorded usage estimate, not an itemized subscription cash charge.
Run identity and stack
- Result ID: space-flight-game-threejs-stage-2-landfall-grok-4.7-xhigh
- Technical model: Grok 4.7
- Provider: Provider not separately recorded
- Client: Grok Build CLI 1.0.41
- Stack: Grok Build CLI 1.0.41
- Stack: Technical model/configuration: Grok 4.7
- Stack: Three.js Stage 2 workflow
- Stack: Harness v1 Landfall prompt
Cost basis
- Server-provided usage/credit value, not proof of cash charged.
Primary artifact integrity
- Kind: manifest-verified-artifact
- Path: artifacts/space-flight-game-threejs-stage-2-landfall-grok-4.7-xhigh/source/src/main.js
- SHA-256: c642c504dab9826e93a7a4c8b32e799f32f89456c596c4d8c8a1b1e57db6c619
Validation evidence
- Result: PASS — model-internal full round trip and limited independent browser check
- Path: artifacts/space-flight-game-threejs-stage-2-landfall-grok-4.7-xhigh/provenance/validation.public.json
- SHA-256: 08669409792576b1433a2aec2838e012c72fc8ce0411e0c30b1ee857965e15d4
Recorded caveats
- The full gameplay completion verdict is Grok’s model-internal checker; the operator performed a separate production build and limited real-key browser check, not an external visual judge.
- Wall-clock is the whole benchmark workflow including tool use, testing and idle intervals, not model-only compute.
- The exact post-generation metrics prompt completed in the same Grok session. Its expected-stack field names the older Grok 4.6/CLI 1.0.3 pair, so stack status is PARTIAL for this intentional Grok 4.7 run.
- Provider-recorded cost is a usage estimate, not proof of marginal cash charged; independent API-equivalent cost remains unavailable for the billed alias.
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.