BuilderBuilder
Benchmark family

Red Sands

Red Sands tests. The v1 release and ledger version v2 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.

← All benchmarks
Western frontier town with a player character and saddled horse in Red Sands v1
Western frontier town with a player character and saddled horse in Red Sands v1
2Variants
5Attached runs
0Related records
1Released material sets
Released materials

Downloads stay on the tests that include them

1 released material set in this family. Variants without a released download stay public evidence.

Western frontier town with a player character and saddled horse in Red Sands v1Three.js / browser

Red Sands v1

  • Prompt
  • 4 projects

4 ready projects

Release smoke proves clean installation, production build, and the fixture smoke route; it does not prove a human completed each authored quest.

Open test materials Open measured runs
Unaided

v1 · Unaided

v1. 1 variant keeps its own prompt receipt and status.

Red Sands

Released Builder materials

4 runs on prompt 7a2e77ceec41

Task red-sands-quest-threejs

SHA-256 7a2e77ceec4154ceac38bf0293d7b10f3e89857bd44a60894d9fbc956898a859

Path benchmarks/fixtures/red-sands-quest-threejs.v1/PROMPT.md

Published Date unreported

Open the released prompt packOpen Red Sands v1 materialsOpen this variant record

Material gaps

  • Repeat-run reliability evidence is not established.

Release smoke proves clean installation, production build, and the fixture smoke route; it does not prove a human completed each authored quest.

The original result ledgers still lack blind evaluation and repeat-run reliability evidence.

Attached runs

  • GPT-5.6 Solartifact_operator_static_checks_ledger_no_playthrough_evidence · Prompt version v1Prompt version v1SHA-256 7a2e77ceec4154ceac38bf0293d7b10f3e89857bd44a60894d9fbc956898a859
  • Kimi K3artifact_model_playthrough_complete_ledger_partial_window_metrics · Prompt version v1Prompt version v1SHA-256 7a2e77ceec4154ceac38bf0293d7b10f3e89857bd44a60894d9fbc956898a859
  • Claude Opus 5artifact_operator_static_checks_ledger_no_playthrough_verification · Prompt version v1Prompt version v1SHA-256 7a2e77ceec4154ceac38bf0293d7b10f3e89857bd44a60894d9fbc956898a859
  • Qwen3.8 Maxartifact_model_playthrough_complete_ledger_partial_metrics · Prompt version v1Prompt version v1SHA-256 7a2e77ceec4154ceac38bf0293d7b10f3e89857bd44a60894d9fbc956898a859

Separate records

No separate unattached record was published for this variant.

Unaided

v2 · Unaided

v2. 1 variant keeps its own prompt receipt and status.

Red Sands · ledger version v2

Public evidence · prompt hash recorded

1 run on prompt 7a2e77ceec41

Task red-sands-quest-threejs

SHA-256 7a2e77ceec4154ceac38bf0293d7b10f3e89857bd44a60894d9fbc956898a859

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.
  • Ledger prompt version is v2. It is not folded into the v1 collection.
  • Repeat-run reliability evidence is not established.

Attached runs

  • Grok 4.6partial_one_shot_metrics_artifact_model_smoke_without_quest_playthrough · Prompt version v2Prompt version v2SHA-256 7a2e77ceec4154ceac38bf0293d7b10f3e89857bd44a60894d9fbc956898a859

Separate records

No separate unattached record was published for this variant.