Measured harness ledgerPublic result
DeepSeek V4 FlashExplorable space-flight game — DeepSeek V4 Flash Max
Build a responsive browser space-flight game with flight controls, a coherent star-system environment, lighting, assets, and a playable game loop.
Max reasoningHeadline result
- Workflow cost
- $0.25
- Wall-clock
- 5h 0m 0.3s wall-clock
- Processed tokens
- 48.16M processed
- Record state
- partial_token_timing_and_artifact_ledger
Public summary
DeepSeek V4 Flash Max partial_token_timing_and_artifact_ledger ledger: 5h 0m 0.3s wall-clock, 48.16M processed, and $0.25 API-equivalent usage accounting, not an itemized subscription cash charge.
Run identity and stack
- Result ID: space-flight-game-deepseek-v4-flash-max
- Technical model: DeepSeek V4 Flash
- Provider: OpenCode Go
- Stack: OpenCode Go
- Stack: Technical model/configuration: DeepSeek V4 Flash
- Stack: Three.js / Vite game
- Stack: Generated spaceship assets
- Stack: Harness v1 space-flight prompt
Cost basis
- Visible output and reasoning are both output-priced. OpenCode Go subscription pricing is not divided into a marginal cash cost for this run.
Primary artifact integrity
- Kind: manifest-verified-artifact
- Path: artifacts/space-flight-game-deepseek-v4-flash-max/source/src/main.js
- SHA-256: 4f90d2303b3af06f4a69ec7de6dad8291476d20847db5891c13e5038e8558532
Validation evidence
- Result: not_run
Recorded caveats
- This is a two-user-turn protocol deviation: the original benchmark prompt needed one ‘continue’ rescue/follow-up turn.
- Wall-clock is end-to-end workflow latency including tool execution, not model-only compute.
- OpenCode splits one agentic turn into multiple assistant/API messages.
- Cache-read tokens are deeply discounted, so total processed tokens overstate cost.
- The public record excludes private OpenCode session/export data; their source hashes and the stable benchmark-window hash are retained.
- No local FPS, RTX Pro 6000 final render, or blind-evaluation record was supplied.
Visible evidence gaps
- one-shot run without an operator rescue turn
- local FPS measurement
- final RTX Pro 6000 1080p60 render or capture metadata
- 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.