dex-draw-mujoco
SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2
Exact prompt file path was not published.
Versioned benchmark collection
Eiffel Tower drawing
Public ledger · prompt hash recorded · 12 measured runs across 1 target. Each entry is a single recorded attempt; repeat-run reliability is not established.
12Measured runs
1Frozen targets
11Model families
12Configurations
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
- Eiffel Tower Drawing
Model coverage
- DeepSeek V4.1 Flash · Highest
- Gemini 3.8 Flash · High
- GLM 5.3 Flash · Highest
- GPT-6 Astra · Low
- GPT-6 Astra · Max
- GPT-6 Sol · Max
- Grok 4.6 · xhigh
- Grok 4.7 · xhigh
- MiMo V2.6 Pro · Highest
- Claude Opus 5 · Max
- Claude Opus 5.5 · Max
- Qwen3.8 Flash · Highest
Evidence available
- 12 runs on prompt ad7b019639be
- Prompt SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2
- 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.
- 7 related records are listed separately and are not attached to this prompt.
- Repeat-run reliability evidence is not established.
Public receipts
12 measured run ledgers
Open any row for its recorded workflow cost, timing, token usage, stack disclosure, artifact integrity, and explicit evidence gaps.
01DeepSeek V4.1 FlashHighest reasoning · Eiffel Tower Drawingjudge_fail_independently_replayed · pass · Prompt version v1$0.08 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate18m 31.4s wall-clockEnd-to-end workflowOpen 02Gemini 3.8 FlashHigh reasoning · Eiffel Tower Drawingjudge_pass_independently_replayed · pass · Prompt version v1$2.72 API-equivalent list price, not a marginal subscription cash chargerecorded estimate8m 25s wall-clockEnd-to-end workflowOpen 03GLM 5.3 FlashHighest reasoning · Eiffel Tower Drawingjudge_pass_independently_replayed · pass · Prompt version v1$0.12 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate10m 28.2s wall-clockEnd-to-end workflowOpen 04GPT-6 AstraLow reasoning · Eiffel Tower Drawingjudge_pass_independently_replayed · PASS · Prompt version v1$1.42 Standard API-equivalent estimate from the Codex wrapper receipt, not a subscription invoice: this was a ChatGPT-subscription run, $0 was charged and Codex emits no cost field.recorded estimate3m 02s wall-clockEnd-to-end workflowOpen 05GPT-6 AstraMax reasoning · Eiffel Tower Drawingjudge_pass_independently_replayed · PASS · Prompt version v1$1.37 Standard API-equivalent estimate from the Codex wrapper receipt, not a subscription invoice: this was a ChatGPT-subscription run, $0 was charged and Codex emits no cost field.recorded estimate4m 10s wall-clockEnd-to-end workflowOpen 06GPT-6 SolMax reasoning · Eiffel Tower Drawingjudge_pass_independently_replayed · PASS · Prompt version v1$0.38 Standard API-equivalent estimate from the Codex wrapper receipt, not a subscription invoice: this was a ChatGPT-subscription run, $0 was charged and Codex emits no cost field.recorded estimate5m 36s wall-clockEnd-to-end workflowOpen 07Grok 4.6xhigh reasoning · Eiffel Tower Drawingjudge_pass_independently_replayed · PASS · Prompt version v1$0.31 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate10m 23s wall-clockEnd-to-end workflowOpen 08Grok 4.7xhigh reasoning · Eiffel Tower Drawingjudge_pass_independently_replayed · PASS · Prompt version v1$2.04 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate19m 18s wall-clockEnd-to-end workflowOpen 09MiMo V2.6 ProHighest reasoning · Eiffel Tower Drawingjudge_pass_independently_replayed · pass · Prompt version v1$0.15 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate36m 58.0s wall-clockEnd-to-end workflowOpen 10Claude Opus 5Max reasoning · Eiffel Tower Drawingjudge_pass_independently_replayed · PASS · Prompt version v1$5.51 API-equivalent estimate from session token counts at Anthropic list price (input $5, output $25, cache read $0.50, cache write $6.25 per MTok)recorded estimate15m 54s wall-clockEnd-to-end workflowOpen 11Claude Opus 5.5Max reasoning · Eiffel Tower Drawingjudge_pass_independently_replayed · PASS · Prompt version v1$2.01 recorded total_cost_usd from workspace FINAL.json (modelUsage.claude-opus-5-5, costBasis=list, Anthropic list price). Charged to the Claude subscription ($0 charged).recorded estimate7m 43s wall-clockEnd-to-end workflowOpen 12Qwen3.8 FlashHighest reasoning · Eiffel Tower Drawingjudge_pass_independently_replayed · pass · Prompt version v1$0.13 Provider-recorded usage estimate, not an itemized subscription cash chargerecorded estimate19m 51.2s 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.