Benchmark family

Rubik’s Cube

Rubik’s Cube single-turn and three-turn tests. Each stage and workflow keeps its own prompt, runs, and status.

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

← All benchmarks

Rubik's cube, single turn public evidence

6Variants

25Attached runs

12Related records

0Released material sets

Unaided

Single turn · Unaided

Single turn. 1 variant keeps its own prompt receipt and status.

Rubik's cube, single turn

Public evidence · prompt hash recorded

12 runs on prompt 9e91081ebac7

Task dex-cube-turn-mujoco

SHA-256 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed

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 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed
Gemini 3.8 Flashjudge_pass_independently_replayed · pass · Prompt version v1Prompt version v1SHA-256 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed
GLM 5.3 Flashjudge_pass_independently_replayed · pass · Prompt version v1Prompt version v1SHA-256 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed
GPT-6 Astrajudge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed
GPT-6 Astrajudge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed
GPT-6 Soljudge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed
Grok 4.6judge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed
Grok 4.7judge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed
MiMo V2.6 Projudge_fail_independently_replayed · pass · Prompt version v1Prompt version v1SHA-256 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed
Claude Opus 5judge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed
Claude Opus 5.5judge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed
Qwen3.8 Flashjudge_fail_independently_replayed · pass · Prompt version v1Prompt version v1SHA-256 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed

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 FlashCampaign judgment: did not pass · 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 FlashCampaign judgment: did not pass · 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 FlashCampaign judgment: pass · 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 FlashCampaign judgment: pass · 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

Single turn · Decision loop

Single turn. 1 variant keeps its own prompt receipt and status.

Rubik's cube, single turn · decision loop

Decision loop · public evidence

1 run on prompt 9e91081ebac7

Task dex-cube-turn-mujoco

SHA-256 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed

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 9e91081ebac7346ce10b9045aa13239bdc8c364c1a064b465f77efa1136bc3ed

Separate records

No separate unattached record was published for this variant.

Astra planner plus Jev

Single turn · Astra planner plus Jev

Single turn. 1 variant keeps its own prompt receipt and status.

Rubik's cube, single turn · Astra planner plus Jev

Supplemental · planner plus Jev

1 run without a prompt hash

Task dex-cube-turn-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.

Attached runs

GPT-6 Astra (low) planner + Jev 1.13 actorjudge_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.

Unaided

Three turns · Unaided

Three turns. 1 variant keeps its own prompt receipt and status.

Rubik's cube, three turns

Public evidence · prompt hash recorded

9 runs on prompt a0839945ff63

Task dex-cube-turn-mujoco-stage-2-three-moves

SHA-256 a0839945ff634a4929e07b52619da37fe48eb30e4415b0ab3ef18c447b3b775c

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.
5 related records are listed separately and are not attached to this prompt.
Repeat-run reliability evidence is not established.
Qwen 3.8 Flash and DeepSeek V4.1 Flash have no Rubik’s Cube three-move extension attempt.

Attached runs

Gemini 3.8 Flashjudge_fail_independently_replayed · pass · Prompt version v1Prompt version v1SHA-256 a0839945ff634a4929e07b52619da37fe48eb30e4415b0ab3ef18c447b3b775c
GLM 5.3 Flashjudge_fail_independently_replayed · pass · Prompt version v1Prompt version v1SHA-256 a0839945ff634a4929e07b52619da37fe48eb30e4415b0ab3ef18c447b3b775c
GPT-6 Astrajudge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 a0839945ff634a4929e07b52619da37fe48eb30e4415b0ab3ef18c447b3b775c
GPT-6 Soljudge_fail_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 a0839945ff634a4929e07b52619da37fe48eb30e4415b0ab3ef18c447b3b775c
Grok 4.6judge_fail_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 a0839945ff634a4929e07b52619da37fe48eb30e4415b0ab3ef18c447b3b775c
Grok 4.7judge_fail_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 a0839945ff634a4929e07b52619da37fe48eb30e4415b0ab3ef18c447b3b775c
MiMo V2.6 Projudge_fail_independently_replayed · pass · Prompt version v1Prompt version v1SHA-256 a0839945ff634a4929e07b52619da37fe48eb30e4415b0ab3ef18c447b3b775c
Claude Opus 5judge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 a0839945ff634a4929e07b52619da37fe48eb30e4415b0ab3ef18c447b3b775c
Claude Opus 5.5judge_pass_independently_replayed · PASS · Prompt version v1Prompt version v1SHA-256 a0839945ff634a4929e07b52619da37fe48eb30e4415b0ab3ef18c447b3b775c

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.
GLM 5.3 FlashCampaign judgment: did not complete · 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 FlashCampaign judgment: did not complete · 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

Three turns · Decision loop

Three turns. 1 variant keeps its own prompt receipt and status.

Rubik's cube, three turns · decision loop

Decision loop · public evidence

1 run on prompt a0839945ff63

Task dex-cube-turn-mujoco-stage-2-three-moves

SHA-256 a0839945ff634a4929e07b52619da37fe48eb30e4415b0ab3ef18c447b3b775c

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 a0839945ff634a4929e07b52619da37fe48eb30e4415b0ab3ef18c447b3b775c

Separate records

No separate unattached record was published for this variant.

Astra Jev hybrid

Three turns · Astra Jev hybrid

Three turns. 1 variant keeps its own prompt receipt and status.

Rubik's cube, three turns · Astra Jev hybrid

Supplemental · Astra Jev hybrid

1 run without a prompt hash

Task dex-cube-turn-mujoco-stage-2-three-moves

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.

Attached runs

GPT-6 Astra planner + Jev 1.13operator_cut_unfinished_episode · 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.