Measured harness ledgerPublic result
Kimi K3Sekiro Main Menu — Kimi K3 Max
Recreate a high-end cinematic Sekiro-style main menu in the browser from the pinned reference and task contract.
Max reasoningHeadline result
- Workflow cost
- Not recorded
- Wall-clock
- 2h 17m 12s wall-clock
- Processed tokens
- Not recorded
- Record state
- partial_metrics_build_verified
Public summary
Kimi K3 Max partial_metrics_build_verified ledger: 2h 17m 12s wall-clock, Not recorded, and Not recorded.
Run identity and stack
- Result ID: sekiro-main-menu-browser-kimi-k3-max
- Technical model: kimi-k3
- Provider: Kimi Code
- Stack: Kimi Code
- Stack: Technical model/configuration: kimi-k3
- Stack: Browser recreation
- Stack: Pinned visual reference
- Stack: Harness v1 Sekiro prompt
Cost basis
- The supplied source gives only a final-state output-token proxy. It has no input, cache, or provider-recorded cost evidence, so a total workflow cost cannot be calculated.
Primary artifact integrity
- Kind: interactive-browser-title-menu-source
- Path: artifacts/sekiro-main-menu-browser-kimi-k3-max/source/index.html
- SHA-256: 62ebef836a8863648f8f15b8260907b423d2b46ab09e58a474ecec71481bf574
Recorded caveats
- This is a partial-metrics entry, not a completed benchmark run. The output-token values are lower-bound proxies from final-state files, not a complete generated-token receipt.
- The archived production build passes, but its 904243-byte JavaScript bundle triggers Vite's non-blocking 500 kB chunk-size advisory.
- No browser or visual evaluation, local FPS, final capture, hardware record, blind-evaluation result, or provider usage evidence was supplied.
Visible evidence gaps
- Complete Kimi session metrics and pricing receipt, including input/cache accounting
- Independent browser interaction and keyboard navigation check
- Local FPS with browser, hardware, and viewport receipt
- Final 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.
