Benchmark family

Eiffel Tower drawing

Eiffel Tower drawing tests. Unaided runs, the decision loop, and the Astra planner plus Jev workflow keep their own prompt records, runs, and status.

Each stage, prompt version, and workflow stays in its own section, with that section's prompt receipt and status.

Eiffel Tower drawing public evidence
Eiffel Tower drawing public evidence
3Variants
14Attached runs
7Related records
0Released material sets
Unaided

Unaided

1 variant keeps its own prompt receipt and status.

Eiffel Tower drawing

Public evidence · prompt hash recorded

12 runs on prompt ad7b019639be

Task dex-draw-mujoco

SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2

Exact prompt file path was not published.

Published Date unreported

No released Builder download is published for this variant.

Open this variant record

Material gaps

  • 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.

Attached runs

  • DeepSeek V4.1 Flashjudge_fail_independently_replayed · pass · Prompt version v1Prompt version v1SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2
  • Gemini 3.8 Flashjudge_pass_independently_replayed · pass · Prompt version v1Prompt version v1SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2
  • GLM 5.3 Flashjudge_pass_independently_replayed · pass · Prompt version v1Prompt version v1SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2
  • GPT-6 Astrajudge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2
  • GPT-6 Astrajudge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2
  • GPT-6 Soljudge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2
  • Grok 4.6judge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2
  • Grok 4.7judge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2
  • MiMo V2.6 Projudge_pass_independently_replayed · pass · Prompt version v1Prompt version v1SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2
  • Claude Opus 5judge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2
  • Claude Opus 5.5judge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2
  • Qwen3.8 Flashjudge_pass_independently_replayed · pass · Prompt version v1Prompt version v1SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2

Separate records

  • GPT-6 Astra + Jev 1.13judge_pass_independently_replayed · Prompt version v1 · Prompt hash unavailablePrompt version v1Prompt hash was not published for this record.Prompt hash was not recorded on this ledger, so it is not attached to the prompt SHA.
  • Qwen 3.8 FlashNo machine-readable validation outcome supplied · Prompt hash unavailablePrompt version was not published.Prompt hash was not published for this record.Launch 005 campaign evidence does not publish a prompt hash, so it is not attached to the prompt SHA.
  • DeepSeek V4.1 FlashNo machine-readable validation outcome supplied · Prompt hash unavailablePrompt version was not published.Prompt hash was not published for this record.Launch 005 campaign evidence does not publish a prompt hash, so it is not attached to the prompt SHA.
  • GLM 5.3 FlashNo machine-readable validation outcome supplied · Prompt hash unavailablePrompt version was not published.Prompt hash was not published for this record.Launch 005 campaign evidence does not publish a prompt hash, so it is not attached to the prompt SHA.
  • Gemini 3.8 FlashEditorial winner; not a machine-validated score · Prompt hash unavailablePrompt version was not published.Prompt hash was not published for this record.Launch 005 campaign evidence does not publish a prompt hash, so it is not attached to the prompt SHA.
  • GPT-6.1 Soljudge_pass_independently_replayed · PASS · Prompt hash unavailablePrompt version was not published.Prompt hash was not published for this record.This Launch 006 record is outside the synced harness expansion, so its prompt hash is not available and it is not attached to the prompt SHA.
  • Claude Sonnet 5.5judge_pass_independently_replayed · PASS · Prompt hash unavailablePrompt version was not published.Prompt hash was not published for this record.This Launch 006 record is outside the synced harness expansion, so its prompt hash is not available and it is not attached to the prompt SHA.
Decision loop

Decision loop

1 variant keeps its own prompt receipt and status.

Eiffel Tower drawing · decision loop

Decision loop · public evidence

1 run on prompt ad7b019639be

Task dex-draw-mujoco

SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2

Exact prompt file path was not published.

Published Date unreported

No released Builder download is published for this variant.

Open this variant record

Material gaps

  • No released Builder project, harness package, or skill download.
  • Exact prompt file path was not published with this test.
  • Repeat-run reliability evidence is not established.

Attached runs

  • Jev 1.13judge_verified_decision_loop_run_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 ad7b019639bee0c901bf9f87dbcecd78c84032a2a679f9cb27f501747830fbe2

Separate records

No separate unattached record was published for this variant.

Astra planner plus Jev

Astra planner plus Jev

1 variant keeps its own prompt receipt and status.

Eiffel drawing, Astra planner plus Jev

Supplemental · planner plus Jev

1 run without a prompt hash

Task dex-draw-mujoco

Prompt hash was not published.

Exact prompt file path was not published.

Published Date unreported

No released Builder download is published for this variant.

Open this variant record

Material gaps

  • No released Builder project, harness package, or skill download.
  • Prompt hash was not recorded on these ledgers.
  • Exact prompt file path was not published with this test.
  • Repeat-run reliability evidence is not established.
  • This supplemental round is only the Astra planner plus Jev workflow.

Attached runs

  • GPT-6 Astra (low) planner + Jev 1.13 actorastra_planner_jev · judge_pass_independently_replayed · Prompt version unreported · Prompt hash unavailablePrompt version unreportedThis attached run has no separate prompt hash.

Separate records

No separate unattached record was published for this variant.