BuilderBuilder
Versioned benchmark collection

Blender Voxel Worlds v1

Harness v1 · Capture protocol v1 · 55 measured runs across 3 targets. Each entry is a single recorded attempt; repeat-run reliability is not established.

Inspect the run ledgers← All collections
Voxel jungle-temple diorama in the Blender Voxel Worlds v1 collection
Voxel jungle-temple diorama in the Blender Voxel Worlds v1 collection
55Measured runs
3Frozen targets
18Model families
22Configurations
Collection scope

Recorded evidence, without a synthetic score.

Each task keeps its own prompt receipt. Runs share a frozen target within each test, with disclosed provider-specific stacks. Costs are recorded estimates as labelled in each ledger, not subscription invoices.

Targets

  • High-voxel-density Jungle Temple diorama
  • High-voxel-density Oasis Outpost diorama
  • High-voxel-density Shrine Village diorama

Model coverage

  • MiMo V2.6 Pro · High
  • Claude Opus 5.5 · High
  • DeepSeek V4 Flash · Max
  • DeepSeek V4 Pro · Max
  • Claude Fable 5 · Max
  • Claude Fable 5 · Medium
  • Claude Fable 5.1 · Max
  • GLM 5.3 Flash · Max
  • GPT-5.6 Luna · xhigh
  • GPT-5.6 Sol · Ultra
  • GPT-5.6 Sol · xhigh
  • GPT-5.6 Terra · Ultra
  • GPT-6 Astra · Max
  • GPT-6 Sol · Max
  • Grok 4.6 · xhigh
  • Grok 4.7 · xhigh
  • Kimi K3 · Max
  • Claude Opus 5 · Max
  • Qwen3.8 Max Preview · Unreported
  • DeepSeek V4 Flash · Vision exp
  • GPT-5.6 Luna · Max
  • Qwen3.8 Flash · Unreported

Evidence available

  • 55 measured run ledgers
  • Primary artifact SHA-256 records
  • Standardized turntable media
  • Prompt SHA-256 acf60b40fee8c1104b91ace024a98631162361f93e52ed852ac01f15e5e28e4c
  • Recorded prompt path benchmarks/prompts/jungle-temple-blender-mcp.v1.md
  • Prompt SHA-256 c2ca9f40a7b067c1928a3afdd2abbb8c979e5e4ce879ba023bdd29e2c6c47736
  • Recorded prompt path benchmarks/prompts/oasis-outpost-blender-mcp.v1.md
  • Prompt SHA-256 e9ab1577c01e37e6ee696a843b69a63a541f4932143f0ac9b9758fac990df55b
  • Recorded prompt path benchmarks/prompts/shrine-village-blender-mcp.v1.md

Still missing

  • Recorded Blender/render environment for original runs
  • Repeat-run evidence
  • Minimum blind-vote sample
  • 15 ledgers in this scope do not record a prompt hash. They remain in the historical scope and are not proof of the frozen prompt.
  • 20 related records are listed separately and are not attached to this prompt.
Public receipts

55 measured run ledgers

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

01MiMo V2.6 ProHigh reasoning · High-voxel-density Jungle Temple dioramamodel_declared_complete_with_viewport_and_structure_validation · Prompt version unreported$0.17 Harness-recorded cost estimate, not an itemized invoicerecorded estimate1544.3s wall-clockEnd-to-end workflowOpen 02Claude Opus 5.5High reasoning · High-voxel-density Jungle Temple dioramaCOMPLETE · PARTIAL · Prompt version unreported$34.98 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 03Claude Opus 5.5High reasoning · High-voxel-density Jungle Temple dioramaPARTIAL · Prompt version unreported$30.01 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 04DeepSeek V4 FlashMax reasoning · High-voxel-density Jungle Temple dioramapartial_token_timing_and_artifact_ledger · not_run · Prompt version v1$0.06 API-equivalent usage accounting, not an itemized subscription cash chargerecorded estimate21m 39.4s wall-clockEnd-to-end workflowOpen 05DeepSeek V4 ProMax reasoning · High-voxel-density Jungle Temple dioramacomplete_token_timing_artifact_and_render_ledger · artifact_and_render_supplied · Prompt version v1$0.13 API-equivalent accounting, not itemized subscription cashrecorded estimate35m 23.3s wall-clockEnd-to-end workflowOpen 06Claude Fable 5Max reasoning · High-voxel-density Jungle Temple dioramapartial_token_timing_and_artifact_ledger · Prompt version v1$79.76 API-equivalent estimate, not a subscription invoicerecorded estimate50:23 wall-clockEnd-to-end workflowOpen 07Claude Fable 5Medium reasoning · High-voxel-density Jungle Temple dioramapartial_token_timing_and_artifact_ledger · 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.$10.10 Anthropic first-party Claude API, standard global pricingrecorded estimate12:04.2 wall-clockEnd-to-end workflowOpen 08Claude Fable 5.1Max reasoning · High-voxel-density Jungle Temple dioramapartial_token_timing_artifact_and_static_source_ledger · PASS · Prompt version v1$22.96 Official Anthropic API-list-price equivalent from the supplied receipt, not an itemized Claude Code subscription charge.recorded estimate50m 20.8s wall-clockEnd-to-end workflowOpen 09GLM 5.3 FlashMax reasoning · High-voxel-density Jungle Temple dioramapartial_multi_user_turn_artifact_ledger · opened_and_source_replayed · Prompt version v1$0.87 OpenCode Go API-equivalent usage accounting, not an itemized subscription marginal-cash invoicerecorded estimate45m 49.093s wall-clockEnd-to-end workflowOpen 10GPT-5.6 Lunaxhigh reasoning · High-voxel-density Jungle Temple dioramapartial_token_timing_and_artifact_ledger · 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.$0.37 API-equivalent estimate, not a subscription invoicerecorded estimate10:55.9 wall-clockEnd-to-end workflowOpen 11GPT-5.6 SolUltra reasoning · High-voxel-density Jungle Temple dioramapartial_token_timing_and_artifact_ledger · 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.$3.23 API-equivalent estimate, not a subscription invoicerecorded estimate26:39.7 wall-clockEnd-to-end workflowOpen 12GPT-5.6 Solxhigh reasoning · High-voxel-density Jungle Temple dioramapartial_token_timing_and_artifact_ledger · 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.$1.69 API-equivalent estimate, not a subscription invoicerecorded estimate10:46.9 wall-clockEnd-to-end workflowOpen 13GPT-5.6 TerraUltra reasoning · High-voxel-density Jungle Temple dioramapartial_token_timing_and_artifact_ledger · 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.$1.20 API-equivalent estimate, not a subscription invoicerecorded estimate16:43.2 wall-clockEnd-to-end workflowOpen 14GPT-6 AstraMax reasoning · High-voxel-density Jungle Temple dioramapartial_post_task_metrics_timing_unavailable_with_blender_scene_open_inspection · Prompt version v1$16.35 Standard API-equivalent estimate from the supplied Codex receipt, not an actual subscription charge.recorded estimateNot recordedEnd-to-end workflowOpen 15GPT-6 SolMax reasoning · High-voxel-density Jungle Temple dioramacomplete_token_timing_artifact_and_validation_ledger · Prompt version unreported$7.81 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 16Grok 4.6xhigh reasoning · High-voxel-density Jungle Temple dioramapartial_one_shot_token_timing_and_artifact_ledger · Prompt version v1$2.11 Official-rate API-equivalent estimate that exactly reconciles to the provider-recorded usage estimate; not a subscription cash-charge invoice.recorded estimate13m 09.039s wall-clockEnd-to-end workflowOpen 17Grok 4.7xhigh reasoning · High-voxel-density Jungle Temple dioramacomplete_internal_model_verdict_with_viewport_only_quality_caveat · Prompt version v1$5.88 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate3304.6s wall-clockEnd-to-end workflowOpen 18Kimi K3Max reasoning · High-voxel-density Jungle Temple dioramapartial_token_timing_and_artifact_ledger · Prompt version v1$2.60 API-equivalent estimate, not an itemized subscription cash chargerecorded estimate53:37.7 wall-clockEnd-to-end workflowOpen 19Claude Opus 5Max reasoning · High-voxel-density Jungle Temple dioramapartial_token_timing_artifact_scene_inspection_ledger · Prompt version v1$40.58 First-party Claude API list-price equivalent, not a subscription invoicerecorded estimate52m 24.4s wall-clockEnd-to-end workflowOpen 20Qwen3.8 Max PreviewUnreported reasoning · High-voxel-density Jungle Temple dioramapartial_token_timing_artifact_validation_ledger · Prompt version v1$6.77 Third-party NanoGPT API-list-price equivalent for the measured token mix; not an Alibaba Token Plan cash chargerecorded estimate48m 49.9s wall-clockEnd-to-end workflowOpen 21DeepSeek V4 FlashVision exp reasoning · High-voxel-density Oasis Outpost dioramaPARTIAL · Prompt version unreported$0.13 Provider-recorded OpenRouter costrecorded estimateNot recordedEnd-to-end workflowOpen 22GLM 5.3 FlashMax reasoning · High-voxel-density Oasis Outpost dioramaFAIL · Prompt version unreported$0.01 Provider-recorded OpenRouter costrecorded estimate15m 35.956s wall-clockEnd-to-end workflowOpen 23GPT-5.6 LunaMax reasoning · High-voxel-density Oasis Outpost dioramaPARTIAL · Prompt version unreportedNot recordedrecorded estimateNot recordedEnd-to-end workflowOpen 24MiMo V2.6 ProHigh reasoning · High-voxel-density Oasis Outpost dioramamodel_declared_complete_with_viewport_and_structure_validation · Prompt version unreported$0.35 Harness-recorded cost estimate, not an itemized invoicerecorded estimate2450.9s wall-clockEnd-to-end workflowOpen 25Claude Opus 5.5High reasoning · High-voxel-density Oasis Outpost dioramaCOMPLETE · Prompt version unreported$43.55 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 26Claude Opus 5.5High reasoning · High-voxel-density Oasis Outpost dioramaPARTIAL · Prompt version unreported$91.43 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 27Qwen3.8 FlashUnreported reasoning · High-voxel-density Oasis Outpost dioramaFAIL · Prompt version unreported$0.19 Provider-recorded OpenRouter costrecorded estimate49m 45.472s wall-clockEnd-to-end workflowOpen 28DeepSeek V4 ProMax reasoning · High-voxel-density Oasis Outpost dioramacomplete_token_timing_artifact_and_render_ledger · artifact_and_render_supplied · Prompt version v1$0.11 API-equivalent accounting, not itemized subscription cashrecorded estimate28m 54.5s wall-clockEnd-to-end workflowOpen 29Claude Fable 5Medium reasoning · High-voxel-density Oasis Outpost dioramapartial_token_timing_and_artifact_ledger · 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.$21.23 Anthropic first-party Claude API, standard global pricingrecorded estimate19:23.7 wall-clockEnd-to-end workflowOpen 30Claude Fable 5.1Max reasoning · High-voxel-density Oasis Outpost dioramapartial_artifact_and_rounded_usage_ledger · Prompt version v1$20.73 provider-reported session cost; not independently recomputable from the rounded displayrecorded estimate58m (rounded provider display) wall-clockEnd-to-end workflowOpen 31GLM 5.3 FlashMax reasoning · High-voxel-density Oasis Outpost dioramapartial_multi_user_turn_artifact_ledger · Prompt version v1$0.23 OpenCode Go API-equivalent usage accounting, not an itemized subscription marginal-cash invoicerecorded estimate35m 0.633s wall-clockEnd-to-end workflowOpen 32GPT-5.6 Lunaxhigh reasoning · High-voxel-density Oasis Outpost dioramapartial_token_timing_and_artifact_ledger · 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.$0.34 API-equivalent estimate, not a subscription invoicerecorded estimate9:43.6 wall-clockEnd-to-end workflowOpen 33GPT-5.6 SolUltra reasoning · High-voxel-density Oasis Outpost dioramapartial_token_timing_and_artifact_ledger · 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.$5.51 API-equivalent estimate, not a subscription invoicerecorded estimate16:30.9 wall-clockEnd-to-end workflowOpen 34GPT-5.6 Solxhigh reasoning · High-voxel-density Oasis Outpost dioramapartial_token_timing_and_artifact_ledger · 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.$1.61 API-equivalent estimate, not a subscription invoicerecorded estimate10:50.3 wall-clockEnd-to-end workflowOpen 35GPT-5.6 TerraUltra reasoning · High-voxel-density Oasis Outpost dioramapartial_token_timing_and_artifact_ledger · 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.$1.33 API-equivalent estimate, not a subscription invoicerecorded estimate28:14.2 wall-clockEnd-to-end workflowOpen 36GPT-6 AstraMax reasoning · High-voxel-density Oasis Outpost dioramapartial_recovered_timing_with_blender_scene_open_inspection · Prompt version v1$10.43 Standard API-equivalent estimate from the supplied Codex receipt, not an actual subscription charge.recorded estimate30m 09.5s (recovered) wall-clockEnd-to-end workflowOpen 37GPT-6 SolMax reasoning · High-voxel-density Oasis Outpost dioramacomplete_token_timing_artifact_and_validation_ledger · Prompt version unreported$9.88 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 38Grok 4.6xhigh reasoning · High-voxel-density Oasis Outpost dioramapartial_one_shot_token_timing_and_artifact_ledger · Prompt version v1$1.78 Provider-recorded usage estimate, not a subscription cash-charge invoicerecorded estimate11m 08.567s wall-clockEnd-to-end workflowOpen 39Kimi K3Max reasoning · High-voxel-density Oasis Outpost dioramapartial_token_timing_and_artifact_ledger · Prompt version v1$2.72 API-equivalent estimate, not an itemized subscription cash chargerecorded estimate39:27.9 wall-clockEnd-to-end workflowOpen 40Claude Opus 5Max reasoning · High-voxel-density Oasis Outpost dioramapartial_token_timing_artifact_scene_inspection_ledger · Prompt version v1$34.68 First-party Claude API list-price equivalent, not a subscription invoicerecorded estimate49m 10.1s wall-clockEnd-to-end workflowOpen 41Qwen3.8 Max PreviewUnreported reasoning · High-voxel-density Oasis Outpost dioramapartial_token_timing_artifact_validation_ledger · Prompt version v1$4.70 Third-party NanoGPT API-list-price equivalent for the measured token mix; not an Alibaba Token Plan cash chargerecorded estimate34m 48.5s wall-clockEnd-to-end workflowOpen 42DeepSeek V4 FlashMax reasoning · High-voxel-density Shrine Village dioramapartial_token_timing_and_artifact_ledger · not_run · Prompt version v1$0.07 API-equivalent usage accounting, not an itemized subscription cash chargerecorded estimate26m 34.3s wall-clockEnd-to-end workflowOpen 43Claude Fable 5Medium reasoning · High-voxel-density Shrine Village dioramapartial_token_timing_and_artifact_ledger · 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.$20.28 Anthropic first-party Claude API, standard global pricingrecorded estimate18:37.5 wall-clockEnd-to-end workflowOpen 44Claude Fable 5.1Max reasoning · High-voxel-density Shrine Village dioramapartial_token_timing_artifact_and_static_source_ledger · PASS · Prompt version v1$76.02 Official Anthropic API-list-price equivalent from the supplied receipt, not an itemized Claude Code subscription charge.recorded estimate53m 25s wall-clockEnd-to-end workflowOpen 45GLM 5.3 FlashMax reasoning · High-voxel-density Shrine Village dioramapartial_multi_user_turn_artifact_ledger · PASS_WITH_CAVEATS · Prompt version v1$1.89 OpenCode Go API-equivalent usage accounting, not an itemized subscription marginal-cash invoicerecorded estimate2h 9m 22.311s wall-clockEnd-to-end workflowOpen 46GPT-5.6 Lunaxhigh reasoning · High-voxel-density Shrine Village dioramapartial_token_timing_and_artifact_ledger · 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.$0.44 API-equivalent estimate, not a subscription invoicerecorded estimate14:02.1 wall-clockEnd-to-end workflowOpen 47GPT-5.6 SolUltra reasoning · High-voxel-density Shrine Village dioramapartial_token_timing_and_artifact_ledger · 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.$1.98 API-equivalent estimate, not a subscription invoicerecorded estimate20:36.2 wall-clockEnd-to-end workflowOpen 48GPT-5.6 Solxhigh reasoning · High-voxel-density Shrine Village dioramapartial_token_timing_and_artifact_ledger · 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.$1.73 API-equivalent estimate, not a subscription invoicerecorded estimate15:10.6 wall-clockEnd-to-end workflowOpen 49GPT-5.6 TerraUltra reasoning · High-voxel-density Shrine Village dioramapartial_token_timing_and_artifact_ledger · 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.$1.30 API-equivalent estimate, not a subscription invoicerecorded estimate19:30.7 wall-clockEnd-to-end workflowOpen 50GPT-6 AstraMax reasoning · High-voxel-density Shrine Village dioramacompleted_generation_turn_with_schema_caveats_and_unverified_render_acceptance · Prompt version v1$9.49 API-equivalent estimate from the completed-generation record, not a subscription invoicerecorded estimate35m 39.2s wall-clockEnd-to-end workflowOpen 51GPT-6 SolMax reasoning · High-voxel-density Shrine Village dioramacomplete_token_timing_artifact_and_validation_ledger · Prompt version unreported$4.28 API-equivalent list price, not a marginal subscription cash chargerecorded estimateNot recordedEnd-to-end workflowOpen 52Grok 4.6xhigh reasoning · High-voxel-density Shrine Village dioramapartial_one_shot_token_timing_and_artifact_ledger · Prompt version v1$2.68 Provider-recorded usage estimate, not a subscription cash-charge invoicerecorded estimate20m 22.040s wall-clockEnd-to-end workflowOpen 53Kimi K3Max reasoning · High-voxel-density Shrine Village dioramapartial_token_timing_and_artifact_ledger · Prompt version v1$2.23 API-equivalent estimate, not an itemized subscription cash chargerecorded estimate35:53.5 wall-clockEnd-to-end workflowOpen 54Claude Opus 5Max reasoning · High-voxel-density Shrine Village dioramapartial_token_timing_artifact_ledger · Prompt version v1$29.67 First-party Claude API list-price equivalent, not a subscription invoicerecorded estimate41m 47.5s wall-clockEnd-to-end workflowOpen 55Qwen3.8 Max PreviewUnreported reasoning · High-voxel-density Shrine Village dioramapartial_token_timing_artifact_validation_ledger · Prompt version v1$3.75 Third-party NanoGPT API-list-price equivalent for the measured token mix; not an Alibaba Token Plan cash chargerecorded estimate30m 59.8s 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.

jungle-temple-blender-mcp

SHA-256 acf60b40fee8c1104b91ace024a98631162361f93e52ed852ac01f15e5e28e4c

Path benchmarks/prompts/jungle-temple-blender-mcp.v1.md

Open the released prompt pack

oasis-outpost-blender-mcp

SHA-256 c2ca9f40a7b067c1928a3afdd2abbb8c979e5e4ce879ba023bdd29e2c6c47736

Path benchmarks/prompts/oasis-outpost-blender-mcp.v1.md

Open the released prompt pack

shrine-village-blender-mcp

SHA-256 e9ab1577c01e37e6ee696a843b69a63a541f4932143f0ac9b9758fac990df55b

Path benchmarks/prompts/shrine-village-blender-mcp.v1.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.

Limits

Evidence and material gaps

  • 7 related records are listed separately and are not attached to this prompt.
  • Repeat-run reliability evidence is not established.
  • 8 related records are listed separately and are not attached to this prompt.
  • 5 related records are listed separately and are not attached to this prompt.