Versioned benchmark collection
Blender Voxel Worlds v1
Harness v1 · Capture protocol v1 · 24 measured runs across 3 targets. Each entry is a single recorded attempt; repeat-run reliability is not established.
24Measured runs
3Frozen targets
7Model families
9Configurations
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
- High-voxel-density Jungle Temple diorama
- High-voxel-density Oasis Outpost diorama
- High-voxel-density Shrine Village diorama
Model coverage
- Claude Fable 5 · Max
- Claude Fable 5 · Medium
- GPT-5.6 Luna · xhigh
- GPT-5.6 Sol · Ultra
- GPT-5.6 Sol · xhigh
- GPT-5.6 Terra · Ultra
- Kimi K3 · Max
- Claude Opus 5 · Max
- Qwen3.8 Max Preview · Unreported
Evidence available
- Twenty-four measured run ledgers
- Primary artifact SHA-256 records
- Standardized turntable media
Still missing
- Recorded Blender/render environment for original runs
- Repeat-run evidence
- Minimum blind-vote sample
Public receipts
24 measured run ledgers
Open any row for its recorded workflow cost, timing, token usage, stack disclosure, artifact integrity, and explicit evidence gaps.
01Claude Fable 5Max reasoning · High-voxel-density Jungle Temple diorama$79.76 API-equivalent estimate, not a subscription invoicerecorded estimate50:23 wall-clockEnd-to-end workflowOpen 02Claude Fable 5Medium reasoning · High-voxel-density Jungle Temple diorama$10.10 Anthropic first-party Claude API, standard global pricingrecorded estimate12:04.2 wall-clockEnd-to-end workflowOpen 03GPT-5.6 Lunaxhigh reasoning · High-voxel-density Jungle Temple diorama$0.37 API-equivalent estimate, not a subscription invoicerecorded estimate10:55.9 wall-clockEnd-to-end workflowOpen 04GPT-5.6 SolUltra reasoning · High-voxel-density Jungle Temple diorama$3.23 API-equivalent estimate, not a subscription invoicerecorded estimate26:39.7 wall-clockEnd-to-end workflowOpen 05GPT-5.6 Solxhigh reasoning · High-voxel-density Jungle Temple diorama$1.69 API-equivalent estimate, not a subscription invoicerecorded estimate10:46.9 wall-clockEnd-to-end workflowOpen 06GPT-5.6 TerraUltra reasoning · High-voxel-density Jungle Temple diorama$1.20 API-equivalent estimate, not a subscription invoicerecorded estimate16:43.2 wall-clockEnd-to-end workflowOpen 07Kimi K3Max reasoning · High-voxel-density Jungle Temple diorama$2.60 API-equivalent estimate, not an itemized subscription cash chargerecorded estimate53:37.7 wall-clockEnd-to-end workflowOpen 08Claude Opus 5Max reasoning · High-voxel-density Jungle Temple diorama$40.58 First-party Claude API list-price equivalent, not a subscription invoicerecorded estimate52m 24.4s wall-clockEnd-to-end workflowOpen 09Qwen3.8 Max PreviewUnreported reasoning · High-voxel-density Jungle Temple diorama$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 10Claude Fable 5Medium reasoning · High-voxel-density Oasis Outpost diorama$21.23 Anthropic first-party Claude API, standard global pricingrecorded estimate19:23.7 wall-clockEnd-to-end workflowOpen 11GPT-5.6 Lunaxhigh reasoning · High-voxel-density Oasis Outpost diorama$0.34 API-equivalent estimate, not a subscription invoicerecorded estimate9:43.6 wall-clockEnd-to-end workflowOpen 12GPT-5.6 SolUltra reasoning · High-voxel-density Oasis Outpost diorama$5.51 API-equivalent estimate, not a subscription invoicerecorded estimate16:30.9 wall-clockEnd-to-end workflowOpen 13GPT-5.6 Solxhigh reasoning · High-voxel-density Oasis Outpost diorama$1.61 API-equivalent estimate, not a subscription invoicerecorded estimate10:50.3 wall-clockEnd-to-end workflowOpen 14GPT-5.6 TerraUltra reasoning · High-voxel-density Oasis Outpost diorama$1.33 API-equivalent estimate, not a subscription invoicerecorded estimate28:14.2 wall-clockEnd-to-end workflowOpen 15Kimi K3Max reasoning · High-voxel-density Oasis Outpost diorama$2.72 API-equivalent estimate, not an itemized subscription cash chargerecorded estimate39:27.9 wall-clockEnd-to-end workflowOpen 16Claude Opus 5Max reasoning · High-voxel-density Oasis Outpost diorama$34.68 First-party Claude API list-price equivalent, not a subscription invoicerecorded estimate49m 10.1s wall-clockEnd-to-end workflowOpen 17Qwen3.8 Max PreviewUnreported reasoning · High-voxel-density Oasis Outpost diorama$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 18Claude Fable 5Medium reasoning · High-voxel-density Shrine Village diorama$20.28 Anthropic first-party Claude API, standard global pricingrecorded estimate18:37.5 wall-clockEnd-to-end workflowOpen 19GPT-5.6 Lunaxhigh reasoning · High-voxel-density Shrine Village diorama$0.44 API-equivalent estimate, not a subscription invoicerecorded estimate14:02.1 wall-clockEnd-to-end workflowOpen 20GPT-5.6 SolUltra reasoning · High-voxel-density Shrine Village diorama$1.98 API-equivalent estimate, not a subscription invoicerecorded estimate20:36.2 wall-clockEnd-to-end workflowOpen 21GPT-5.6 Solxhigh reasoning · High-voxel-density Shrine Village diorama$1.73 API-equivalent estimate, not a subscription invoicerecorded estimate15:10.6 wall-clockEnd-to-end workflowOpen 22GPT-5.6 TerraUltra reasoning · High-voxel-density Shrine Village diorama$1.30 API-equivalent estimate, not a subscription invoicerecorded estimate19:30.7 wall-clockEnd-to-end workflowOpen 23Kimi K3Max reasoning · High-voxel-density Shrine Village diorama$2.23 API-equivalent estimate, not an itemized subscription cash chargerecorded estimate35:53.5 wall-clockEnd-to-end workflowOpen 24Qwen3.8 Max PreviewUnreported reasoning · High-voxel-density Shrine Village diorama$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