Measured harness ledgerPublic result
GPT-6 Sol

Space Flight Stage 2 — Landfall — GPT-6 Sol Max

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.

Max reasoningHeadline result
Workflow cost
$7.02
Wall-clock
4707.4s wall-clock
Processed tokens
Not recorded
Record state
complete_by_model_internal_verdict_with_qualified_visual_and_perf_scope
Public summary

GPT-6 Sol Max complete_by_model_internal_verdict_with_qualified_visual_and_perf_scope ledger: 4707.4s wall-clock, Not recorded, and $7.02 API-equivalent list price, not a marginal subscription cash charge.

Run identity and stack
  • Result ID: space-flight-game-threejs-stage-2-landfall-gpt-6-sol-max
  • Technical model: gpt-6-sol
  • Provider: OpenAI Codex CLI
  • Stack: OpenAI Codex CLI
  • Stack: Technical model/configuration: gpt-6-sol
  • Stack: Three.js Stage 2 workflow
  • Stack: Harness v1 Landfall prompt
Primary artifact integrity
  • Kind: manifest-verified-artifact
  • Path: artifacts/space-flight-game-threejs-stage-2-landfall-gpt-6-sol-max/source/src/main.js
  • SHA-256: 743e156f21899a7eb0f1ecca1f22dfc24dfaa74cdaca357fc71eb5c8d121b866
Validation evidence
  • Path: artifacts/space-flight-game-threejs-stage-2-landfall-gpt-6-sol-max/verification/archive-build.public.json
  • SHA-256: 1bab0414047abd8fd2a4d5fc4bc5a031320182d3f487f25833f441d63a447172
Recorded caveats
  • Stage 2 was built from the exact archived Stage 1 source baseline; its parent snapshot and SHA-256 manifest are preserved.
  • The supplied API-equivalent estimate is not an itemized Codex subscription charge.
  • The model judged the orbit/ground/foot/orbit loop complete. Its own stated limits: the fracture seam remains subtle and landmarks have no prop collision.
  • The two-cycle Chrome frame sample is host-specific and not a universal performance guarantee.
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.

RemakeBenchResearch console