BuilderBuilder
Launch 005 · direct campaign footage

Rubik’s Cube three-move extension — Gemini 3.8 Flash

Neither GLM nor Gemini completed the harder three-move extension.

Displayed cost
$5.65
Wall clock
44m 30s
Record type
Campaign evidence
Validation
Campaign judgment: did not complete

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. Only the two single-turn passers advanced. Qwen and DeepSeek have no three-move attempt and are shown as did not advance, not as missing or failed runs.

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

Rubik’s Cube three-move extension — Gemini 3.8 Flash · Launch 005 campaign evidence

Use the dexterous robot-hand fixture to complete the harder three-move Rubik’s Cube extension after advancing from the single-turn task.

High reasoningHeadline result
Workflow cost
$5.65
Wall-clock
44m 30s
Processed tokens
Unavailable
Record state
campaign_evidence_not_harness_ledger
Public summary

Gemini 3.8 Flash Rubik’s Cube three-move extension campaign-evidence record: 44m 30s wall clock and $5.65 displayed cost.

Run identity and stack
  • Result ID: dex-cube-three-move-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 three-move extension 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: Three Move Cube
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: did not complete
  • 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.
  • Only GLM and Gemini advanced to this extension; no Qwen or DeepSeek three-move attempt exists.
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