Measured harness ledgerPublic result
DeepSeek V4 Flash

Space Flight Stage 2 — Landfall — DeepSeek V4 Flash 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
$0.27
Wall-clock
4h 36m 23.0s wall-clock
Processed tokens
60.51M processed
Record state
partial_token_timing_source_build_ledger
Public summary

DeepSeek V4 Flash Max partial_token_timing_source_build_ledger ledger: 4h 36m 23.0s wall-clock, 60.51M processed, and $0.27 API-equivalent usage accounting, not an itemized subscription cash charge.

Run identity and stack
  • Result ID: space-flight-game-threejs-stage-2-landfall-deepseek-v4-flash-max
  • Technical model: DeepSeek V4 Flash
  • Provider: OpenCode Go
  • Client: OpenCode
  • Stack: OpenCode Go
  • Stack: OpenCode
  • Stack: Technical model/configuration: DeepSeek V4 Flash
  • Stack: Three.js Stage 2 workflow
  • Stack: Harness v1 Landfall 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: archive-of-user-supplied-vite-production-build
  • Path: artifacts/space-flight-game-threejs-stage-2-landfall-deepseek-v4-flash-max/production-build.tar.gz
  • SHA-256: c051dc530a7c3cd8ff56bedf0a55b24c95283394aa576e8968585b8f90cbfcb8
Validation evidence
  • Result: not_run
Recorded caveats
  • This is a two-user-turn protocol deviation: the bounded benchmark window includes one operator follow-up/rescue turn.
  • Wall-clock is end-to-end workflow latency including tool execution, installs, browser checks, and idle time; it is not model-only compute.
  • OpenCode splits an 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.
  • The supplied source bundle and pre-existing production build are archived without a fresh independent build or runtime check. The included screenshots are model-provided evidence only.
  • No local FPS, transition-hitch receipt, RTX Pro 6000 final render, or blind-evaluation record was supplied.
Visible evidence gaps
  • one-shot run without an operator rescue turn
  • independent full-loop browser acceptance run
  • local FPS and transition-hitch 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.

RemakeBenchResearch console