courtyard-arena-blossom-stage-2-reference-exposed
SHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
Exact prompt file path was not published.
Versioned benchmark collection
Blossom arena
Public ledger · prompt hash recorded · 15 measured runs across 1 target. Each entry is a single recorded attempt; repeat-run reliability is not established.
15Measured runs
1Frozen targets
12Model families
14Configurations
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
- Claude Opus 5 · Max
- DeepSeek V4 Flash · Vision exp
- DeepSeek V4.1 Flash · Highest
- Claude Fable 5.1 · Max
- Gemini 3.8 Flash · Highest
- GLM 5.3 Flash · Max
- GLM 5.3 Flash · Highest
- GPT-5.6 Luna · Max
- GPT-6 Astra · Max
- GPT-6 Sol · Max
- MiMo V2.6 Pro · High
- Claude Opus 5.5 · High
- Qwen3.8 Flash · Unreported
- Qwen3.8 Flash · Highest
Evidence available
- 15 runs on prompt f6fa6f04d354
- Prompt SHA-256 f6fa6f04d354230dfd90c4f8b3dad7100db5747d4352ddea8b17d63eccbb8973
- Exact prompt file path was not published
Still missing
- 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.
Public receipts
15 measured run ledgers
Open any row for its recorded workflow cost, timing, token usage, stack disclosure, artifact integrity, and explicit evidence gaps.
01Claude Opus 5Max reasoning · Courtyard Blossom Stage 2artifact_and_final_metrics_ledger_no_independent_browser_replay · Prompt version v1$98.04 Claude API list-price equivalent, not an itemized Claude Code subscription chargerecorded estimate1h 20m 48.3s wall-clockEnd-to-end workflowOpen 02DeepSeek V4 FlashVision exp reasoning · Courtyard Blossom Stage 2PARTIAL · Prompt version unreported$0.46 Provider-recorded OpenRouter costrecorded estimateNot recordedEnd-to-end workflowOpen 03DeepSeek V4.1 FlashHighest reasoning · Courtyard Blossom Stage 2complete_token_timing_artifact_and_validation_ledger · pass · Prompt version unreported$0.36 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate3599.2s wall-clockEnd-to-end workflowOpen 04Claude Fable 5.1Max reasoning · Courtyard Blossom Stage 2artifact_and_sanitized_metrics_with_independent_in_app_browser_replay · Prompt version v1$237.58 Claude API list-price equivalent, not an itemized Claude Code subscription chargerecorded estimate2h 35m 15.1s wall-clockEnd-to-end workflowOpen 05Gemini 3.8 FlashHighest reasoning · Courtyard Blossom Stage 2complete_token_timing_artifact_and_validation_ledger · pass_with_visual_caveat · Prompt version unreported$5.02 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate2838.7s wall-clockEnd-to-end workflowOpen 06GLM 5.3 FlashMax reasoning · Courtyard Blossom Stage 2FAIL · Prompt version unreported$0.68 Provider-recorded OpenRouter costrecorded estimate1h 45m 16.069s wall-clockEnd-to-end workflowOpen 07GLM 5.3 FlashHighest reasoning · Courtyard Blossom Stage 2complete_token_timing_artifact_and_validation_ledger · pass · Prompt version unreported$0.79 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate5868.2s wall-clockEnd-to-end workflowOpen 08GPT-5.6 LunaMax reasoning · Courtyard Blossom Stage 2PENDING_JUDGE · Prompt version unreportedNot recordedrecorded estimateNot recordedEnd-to-end workflowOpen 09GPT-6 AstraMax reasoning · Courtyard Blossom Stage 2partial_root_snapshot_metrics_with_independent_in_app_browser_replay_and_unverified_model_geometry_evidence · Prompt version v1$74.50 OpenAI Standard API-list-price equivalent, not an itemized Codex subscription chargerecorded estimateNot recordedEnd-to-end workflowOpen 10GPT-6 SolMax reasoning · Courtyard Blossom Stage 2complete_token_timing_artifact_and_validation_ledger · Prompt version unreported$19.52 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 11MiMo V2.6 ProHigh reasoning · Courtyard Blossom Stage 2model_declared_complete_with_operator_qualifications · Prompt version unreported$0.65 OpenCode-recorded cost, not an itemized subscription cash chargerecorded estimate10126.5s wall-clockEnd-to-end workflowOpen 12Claude Opus 5.5High reasoning · Courtyard Blossom Stage 2COMPLETE · Prompt version unreported$309.00 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 13Claude Opus 5.5High reasoning · Courtyard Blossom Stage 2PARTIAL · Prompt version unreported$433.73 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 14Qwen3.8 FlashUnreported reasoning · Courtyard Blossom Stage 2FAIL · Prompt version unreported$0.71 Provider-recorded OpenRouter costrecorded estimate1h 33m 46.679s wall-clockEnd-to-end workflowOpen 15Qwen3.8 FlashHighest reasoning · Courtyard Blossom Stage 2complete_token_timing_artifact_and_validation_ledger · pass · Prompt version unreported$1.17 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate9309.1s 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.
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.