BuilderBuilder
Versioned benchmark collection

Blossom arena

Public ledger · prompt hash recorded · 1 measured runs across 1 target. Each entry is a single recorded attempt; repeat-run reliability is not established.

Inspect the run ledgers← All collections
No published still for Blossom arena
1Measured runs
1Frozen targets
1Model families
1Configurations
Collection scope

Recorded evidence, without a synthetic score.

Runs share the same frozen target and prompt within each test, with disclosed provider-specific stacks. Costs are recorded estimates as labelled in each ledger, not subscription invoices.

Targets

  • Courtyard Blossom Stage 2

Model coverage

  • Grok 4.6 · xhigh

Evidence available

  • 1 run on prompt 672b3d3ed257
  • Prompt SHA-256 672b3d3ed257358e5f7ba780f2f06e2f35194734cad0152c653010a33cd081a6
  • Recorded prompt path benchmarks/fixtures/courtyard-arena-blender-mcp.v1/PROMPT.md

Still missing

  • No released Builder project, harness package, or skill download.
  • The recorded prompt path is not a released download.
  • Non-scoring ledger status: delivered_playable_stage_2_artifact_non_scoring.
  • This prompt SHA matches the released Fighter Game v1 prompt, not the other blossom-arena ledgers.
  • Repeat-run reliability evidence is not established.
Public receipts

1 measured run ledgers

Open any row for its recorded workflow cost, timing, token usage, stack disclosure, artifact integrity, and explicit evidence gaps.

01Grok 4.6xhigh reasoning · Courtyard Blossom Stage 2delivered_playable_stage_2_artifact_non_scoring · PASS_WITH_NONCOMPARABILITY · Prompt version v1$9.22 Provider-recorded usage estimate, not a subscription cash-charge invoicerecorded estimate22m 49.670s wall-clockEnd-to-end workflowOpen
Prompt provenance

Exact prompt receipts

A path is shown only when the published record includes the prompt hash that identifies it. Campaign evidence and projections keep the hash gap visible.

courtyard-arena-blossom-stage-2-reference-exposed

SHA-256 672b3d3ed257358e5f7ba780f2f06e2f35194734cad0152c653010a33cd081a6

Path benchmarks/fixtures/courtyard-arena-blender-mcp.v1/PROMPT.md

Open the released prompt pack
Separate records

Related records with unknown prompt provenance

These published records stay separate from the prompt receipts above. Unknown provenance is why they are listed here.

No separate unattached records are published for this collection.