Launch 005 · direct campaign footage

Turbofan CADGLM 5.3 Flash

DeepSeek delivered the better submitted CAD result. Gemini produced valid solids but did not complete the required delivery; Qwen timed out and GLM truncated without native geometry.

Displayed cost
$0.215242
Wall clock
50m 37s
Record type
Campaign evidence
Validation
No source or native geometry delivered

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. Gemini’s operator-created assembly and presentation clip are post-run work, never model-completed scored motion evidence.

Open the four-way fixture
GLM 5.3 Flash · Turbofan CAD presentation recording poster
Muted loop · poster first · pauses offscreen · reduced-motion poster
Campaign evidence recordPublic result
GLM 5.3 Flash

Turbofan CAD — GLM 5.3 Flash · Launch 005 campaign evidence

Create the CAD-001 v1.0.1 turbofan submission under the campaign’s native-CAD delivery contract.

Max reasoningHeadline result
Workflow cost
$0.215242
Wall-clock
50m 37s
Processed tokens
Unavailable
Record state
campaign_evidence_not_harness_ledger
Public summary

GLM 5.3 Flash Turbofan CAD campaign-evidence record: 50m 37s wall clock and $0.215242 displayed cost.

Run identity and stack
  • Result ID: turbofan-engine-glm-5-3-flash-launch-005-campaign-evidence
  • Technical model: opencode-go/glm-5.3-flash
  • Provider: OpenCode Go
  • Client: OpenCode 1.18.23
  • Stack: Launch 005 video campaign evidence
  • Stack: Exact Turbofan CAD presentation clip
  • Stack: Not generated from the public Harness ledger
  • Stack: Search alias: Turbofan
  • Stack: Search alias: Turbofan Engine
  • Stack: Search alias: CAD-001
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 source or native geometry delivered
  • Verification: Committed campaign CAD report.
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.
  • The effective output-limit discrepancy remains unresolved, so this is not a clean numerical measure of GLM’s CAD capability.
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