BuilderBuilder
Benchmark family

Blossom arena

Blossom arena tests. Each prompt hash keeps its own runs and status.

Each stage, prompt version, and workflow stays in its own section, with that section's prompt receipt and status.

← All benchmarks
Blossom arena public evidence
Blossom arena public evidence
2Variants
16Attached runs
3Related records
0Released material sets
Unaided

Prompt 672b3d3ed257 · Unaided

1 variant keeps its own prompt receipt and status.

Blossom arena

Non-scoring · delivered_playable_stage_2_artifact_non_scoring

1 run on prompt 672b3d3ed257

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

SHA-256 672b3d3ed257358e5f7ba780f2f06e2f35194734cad0152c653010a33cd081a6

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

Published Date unreported

Open the released prompt pack

No released Builder download is published for this variant.

Open this variant record

Material gaps

  • 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.

Attached runs

  • Grok 4.6delivered_playable_stage_2_artifact_non_scoring · PASS_WITH_NONCOMPARABILITY · Prompt version v1Prompt version v1SHA-256 672b3d3ed257358e5f7ba780f2f06e2f35194734cad0152c653010a33cd081a6

Separate records

No separate unattached record was published for this variant.

Unaided

Prompt f6fa6f04d354 · Unaided

1 variant keeps its own prompt receipt and status.

Blossom arena

Public evidence · prompt hash recorded

15 runs on prompt f6fa6f04d354

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

SHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973

Exact prompt file path was not published.

Published Date unreported

No released Builder download is published for this variant.

Open this variant record

Material gaps

  • No released Builder project, harness package, or skill download.
  • Exact prompt file path was not published with this test.
  • 3 related records are listed separately and are not attached to this prompt.
  • Repeat-run reliability evidence is not established.

Attached runs

  • Claude Opus 5artifact_and_final_metrics_ledger_no_independent_browser_replay · Prompt version v1Prompt version v1SHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • DeepSeek V4 FlashPARTIAL · Prompt version unreportedPrompt version unreportedSHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • DeepSeek V4.1 Flashcomplete_token_timing_artifact_and_validation_ledger · pass · Prompt version unreportedPrompt version unreportedSHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • Claude Fable 5.1artifact_and_sanitized_metrics_with_independent_in_app_browser_replay · Prompt version v1Prompt version v1SHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • Gemini 3.8 Flashcomplete_token_timing_artifact_and_validation_ledger · pass_with_visual_caveat · Prompt version unreportedPrompt version unreportedSHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • GLM 5.3 FlashFAIL · Prompt version unreportedPrompt version unreportedSHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • GLM 5.3 Flashcomplete_token_timing_artifact_and_validation_ledger · pass · Prompt version unreportedPrompt version unreportedSHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • GPT-5.6 LunaPENDING_JUDGE · Prompt version unreportedPrompt version unreportedSHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • GPT-6 Astrapartial_root_snapshot_metrics_with_independent_in_app_browser_replay_and_unverified_model_geometry_evidence · Prompt version v1Prompt version v1SHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • GPT-6 Solcomplete_token_timing_artifact_and_validation_ledger · Prompt version unreportedPrompt version unreportedSHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • MiMo V2.6 Promodel_declared_complete_with_operator_qualifications · Prompt version unreportedPrompt version unreportedSHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • Claude Opus 5.5COMPLETE · Prompt version unreportedPrompt version unreportedSHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • Claude Opus 5.5PARTIAL · Prompt version unreportedPrompt version unreportedSHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • Qwen3.8 FlashFAIL · Prompt version unreportedPrompt version unreportedSHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
  • Qwen3.8 Flashcomplete_token_timing_artifact_and_validation_ledger · pass · Prompt version unreportedPrompt version unreportedSHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973

Separate records

  • Grok 4.7verified_runtime_with_visual_performance_and_acceptance_qualifications · Prompt version unreported · Prompt hash unavailablePrompt version unreportedPrompt hash was not published for this record.Prompt hash was not recorded on this ledger, so it is not attached to the prompt SHA.
  • Claude Sonnet 5.5partial_user_stopped · PARTIAL · Prompt hash unavailablePrompt version was not published.Prompt hash was not published for this record.This Launch 006 record is outside the synced harness expansion, so its prompt hash is not available and it is not attached to the prompt SHA.
  • GPT-6.1 Solpartial_user_stopped · STOPPED_PARTIAL · Prompt hash unavailablePrompt version was not published.Prompt hash was not published for this record.This Launch 006 record is outside the synced harness expansion, so its prompt hash is not available and it is not attached to the prompt SHA.