macbook-cinematic-blender-mcp
SHA-256 2b59b47d3dc5d4e51418c9fa9d08092f5034c70f4632252cbc72a2228633cc1c
Path benchmarks/prompts/macbook-cinematic-blender-mcp.v1.md
Versioned benchmark collection
MacBook Cinematic v1
Harness v1 · 10 measured runs across 1 target. Each entry is a single recorded attempt; repeat-run reliability is not established.
10Measured runs
1Frozen targets
10Model families
10Configurations
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
- MacBook-class cinematic ad scene
Model coverage
- DeepSeek V4 Flash · Max
- Claude Fable 5 · Max
- Claude Fable 5.1 · Max
- GPT-5.6 Sol · xhigh
- GPT-6 Astra · Max
- Grok 4.6 · xhigh
- Kimi K3 · Max
- Claude Opus 5 · Max
- Qwen3.8 Max Preview · Mandatory thinking enabled
- Qwen3.8 Max · xhigh
Evidence available
- 10 measured run ledgers
- Public recorded outputs
- Cost, token, and workflow timing
- Prompt SHA-256 2b59b47d3dc5d4e51418c9fa9d08092f5034c70f4632252cbc72a2228633cc1c
- Recorded prompt path benchmarks/prompts/macbook-cinematic-blender-mcp.v1.md
Still missing
- One reconciled Kimi API request
- Repeat-run reliability evidence
- Minimum blind-vote sample
- 1 ledgers in this scope do not record a prompt hash. They remain in the historical scope and are not proof of the frozen prompt.
- 2 related records are listed separately and are not attached to this prompt.
Public receipts
10 measured run ledgers
Open any row for its recorded workflow cost, timing, token usage, stack disclosure, artifact integrity, and explicit evidence gaps.
01DeepSeek V4 FlashMax reasoning · MacBook-class cinematic ad scenepartial_token_timing_artifact_validation_ledger · PASS, 49/49 checks · Prompt version v1$0.60 API-equivalent usage accounting, not an itemized subscription cash chargerecorded estimate2h 51m 8.5s wall-clockEnd-to-end workflowOpen 02Claude Fable 5Max reasoning · MacBook-class cinematic ad scenepartial_token_timing_artifact_validation_ledger · PASS, 49/49 checks · Prompt version v1$75.18 API-equivalent estimate, not a subscription invoicerecorded estimate1:01:04.8 wall-clockEnd-to-end workflowOpen 03Claude Fable 5.1Max reasoning · MacBook-class cinematic ad scenepartial_active_session_snapshot_with_supplied_validation · PASS, 49/49 supplied checks · Prompt version v1$171.34 Official Anthropic API-list-price equivalent from the supplied active-session snapshot, not a Claude Code subscription invoice.recorded estimate5h 19m 27.3s wall-clockEnd-to-end workflowOpen 04GPT-5.6 Solxhigh reasoning · MacBook-class cinematic ad scenepartial_token_timing_artifact_validation_ledger · PASS, 49/49 checks · Prompt version v1$7.67 API-equivalent estimate, not a subscription invoicerecorded estimate55:49.9 wall-clockEnd-to-end workflowOpen 05GPT-6 AstraMax reasoning · MacBook-class cinematic ad scenepartial_post_task_metrics_snapshot_with_independent_validation · 49/49 checks recorded · Prompt version v1$20.35 API-equivalent estimate from a qualified post-task snapshot, not a subscription invoicerecorded estimate65m 04s (qualified snapshot span) wall-clockEnd-to-end workflowOpen 06Grok 4.6xhigh reasoning · MacBook-class cinematic ad scenepartial_one_shot_token_timing_artifact_validation_ledger · 49/49 checks recorded · Prompt version v1$5.58 Provider-recorded usage estimate, not a subscription cash-charge invoicerecorded estimate30m 14.028s wall-clockEnd-to-end workflowOpen 07Kimi K3Max reasoning · MacBook-class cinematic ad scenepartial_token_timing_artifact_validation_ledger · PASS, 49/49 checks · Prompt version v1≥$10.85 API-equivalent lower bound over paired usage records, not an itemized subscription cash charge (lower bound)recorded lower bound1:26:58.2 wall-clockEnd-to-end workflowOpen 08Claude Opus 5Max reasoning · MacBook-class cinematic ad scenepartial_token_timing_and_artifact_ledger · PASS — 49/49 · Prompt version v1$27.40 API-equivalent estimate, not a subscription invoicerecorded estimate1h 07m 02.5s wall-clockEnd-to-end workflowOpen 09Qwen3.8 Max PreviewMandatory thinking enabled reasoning · MacBook-class cinematic ad scenepartial_objective_pass_agent_nontermination · 49/49 checks recorded · Prompt version v1 · Prompt hash unavailablePrompt hash was not recorded on this historical ledger. It stays in the historical collection scope and is not proof of the frozen prompt.$29.27 Qualified third-party NanoGPT API-list-price scenario; not an Alibaba Token Plan cash chargerecorded estimate7h 00m 56.4s wall-clockEnd-to-end workflowOpen 10Qwen3.8 Maxxhigh reasoning · MacBook-class cinematic ad sceneartifact_validator_pass_metrics_partial_quota_interrupted · 49/49 checks recorded · Prompt version v1$24.99 API-equivalent accounting only, not an itemized Token Plan cash chargerecorded estimate2h 51m 49.9s 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.
Limits
Evidence and material gaps
- Repeat-run reliability evidence is not established.