DeepSeek V4.1 Flash · Eiffel Tower drawing presentation recording poster
Gemini was the editorial winner and the fastest shown Eiffel Tower attempt at 8m 25s. Compare all four models
Campaign evidence recordPublic result
DeepSeek V4.1 Flash

Eiffel Tower drawing — DeepSeek V4.1 Flash · Launch 005 campaign evidence

Use the robot drawing fixture to produce the Eiffel Tower drawing shown in the Launch 005 campaign.

Max reasoningHeadline result
Workflow cost
$0.0841
Wall-clock
18m 31.4s
Processed tokens
Unavailable
Record state
campaign_evidence_not_harness_ledger
Public summary

DeepSeek V4.1 Flash Eiffel Tower drawing campaign-evidence record: 18m 31.4s wall clock and $0.0841 displayed cost.

Run identity and stack
  • Result ID: eiffel-tower-drawing-deepseek-v4-1-flash-launch-005-campaign-evidence
  • Technical model: DeepSeek V4.1 Flash
  • Provider: Unavailable
  • Client: Unavailable
  • Stack: Launch 005 video campaign evidence
  • Stack: Exact Eiffel Tower drawing presentation clip
  • Stack: Not generated from the public Harness ledger
  • Stack: Search alias: Eiffel Tower
  • Stack: Search alias: Eiffel Tower Drawing
  • Stack: Search alias: Robot Drawing
Cost basis
  • Exact displayed cost from the owner-supplied Launch 005 media handoff.
  • Campaign clip metric scope; not a substitute for a missing provider invoice or Harness ledger.
Validation evidence
  • Result: No machine-readable validation outcome supplied
  • Verification: Video-campaign judgment; no machine-readable Harness validator was supplied.
Recorded caveats
  • Campaign-evidence record; this attempt was not generated from the public Harness ledger.
  • Provider, client, token usage, prompt hash, validator output, and attempt number are unavailable unless separately disclosed.
  • The published clip is direct visual evidence, not standardized FPS or hardware evidence.
Visible evidence gaps
  • public Harness ledger provenance
  • provider/client receipt unless separately disclosed
  • token usage
  • prompt hash
  • machine-readable validator output
  • repeat-run evidence
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