BuilderBuilder
Launch 005 · direct campaign footage

Rubik’s Cube single turn — Gemini 3.8 Flash

GLM and Gemini completed the single-turn task; Gemini was fastest. Qwen and DeepSeek did not complete it.

Displayed cost
$2.09
Wall clock
15m 35s
Record type
Campaign evidence
Validation
Campaign judgment: pass

Metric boundary. This permanent campaign-evidence record uses the handoff’s exact displayed cost and wall clock; it is not a generated Harness ledger.

Evidence boundary. Pass/fail labels are video-campaign judgments. No machine-readable robot validator was supplied.

Open the four-way fixture
Gemini 3.8 Flash · Rubik’s Cube single turn presentation recording poster
Muted loop · poster first · pauses offscreen · reduced-motion poster
Campaign evidence recordPublic result
Gemini 3.8 Flash

Rubik’s Cube single turn — Gemini 3.8 Flash · Launch 005 campaign evidence

Use the dexterous robot-hand fixture to complete the campaign’s single-turn Rubik’s Cube task.

High reasoningHeadline result
Workflow cost
$2.09
Wall-clock
15m 35s
Processed tokens
Unavailable
Record state
campaign_evidence_not_harness_ledger
Public summary

Gemini 3.8 Flash Rubik’s Cube single turn campaign-evidence record: 15m 35s wall clock and $2.09 displayed cost.

Run identity and stack
  • Result ID: dex-cube-turn-gemini-3-8-flash-launch-005-campaign-evidence
  • Technical model: Gemini 3.8 Flash
  • Provider: Unavailable
  • Client: Unavailable
  • Stack: Launch 005 video campaign evidence
  • Stack: Exact Rubik’s Cube single turn presentation clip
  • Stack: Not generated from the public Harness ledger
  • Stack: Search alias: Dex Cube
  • Stack: Search alias: Rubik’s Cube
  • Stack: Search alias: Rubiks Cube
  • Stack: Search alias: Cube Turn
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: Campaign judgment: pass
  • 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.

Browse BuilderReturn to Gemini 3.8 Flash
RemakeBenchResearch console