Measured harness ledgerPublic result
GLM 5.3 Flash

Courtyard Blossom Stage 2 — GLM 5.3 Flash Highest

Create a second cherry-blossom temple courtyard arena for the fixed fighting game under the pinned reference-guided Stage 2 contract.

Highest reasoningHeadline result
Workflow cost
$0.79
Wall-clock
5868.2s wall-clock
Processed tokens
35.27M processed
Record state
complete_token_timing_artifact_and_validation_ledger
Public summary

GLM 5.3 Flash Highest complete_token_timing_artifact_and_validation_ledger ledger: 5868.2s wall-clock, 35.27M processed, and $0.79 Provider-recorded usage estimate, not an itemized subscription cash charge.

Run identity and stack
  • Result ID: courtyard-arena-blossom-stage-2-reference-exposed-glm-5.3-flash-max-opencode-openrouter-2026-09-04
  • Technical model: GLM 5.3 Flash
  • Provider: OpenRouter
  • Client: OpenCode 1.18.23
  • Variant: max
  • Stack: OpenRouter
  • Stack: OpenCode 1.18.23
  • Stack: OpenCode → OpenRouter
  • Stack: Technical model/configuration: GLM 5.3 Flash
  • Stack: Requested variant: max
  • Stack: Blender / browser arena workflow
  • Stack: Reference-guided Stage 2 fixture
Primary artifact integrity
  • Kind: manifest-verified-artifact
  • Path: artifacts/courtyard-arena-blossom-stage-2-reference-exposed-glm-5.3-flash-max-opencode-openrouter-2026-09-04/source/blender/arena_cherry.blend
  • SHA-256: 776578dde9172a40a2c4d926f29e9c38cd66a2eb1e55cd4b3aea23783a01a259
Validation evidence
  • Result: pass
  • Path: artifacts/courtyard-arena-blossom-stage-2-reference-exposed-glm-5.3-flash-max-opencode-openrouter-2026-09-04/verification/summary.public.json
  • SHA-256: ab72884627d63349674c2e20205fb2958f3740569f828c0ae84787fc0a50c37c
Recorded caveats
  • No blind visual quality score is attached.
  • The bounded metrics extractor marked protocol compliance PARTIAL because the build used continuation turns.
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