Lava lamp v1 · Codex CLI · run 4716ed3f · 18.11.2026 00:22 Tallinn

GPT-6.2 Astra

Extra high effort

Works

8 of 8 checks passed. All 5 blocker checks passed.

What it built: 3 captures

Desktop capture of Codex CLI (GPT-6.2 Astra)'s output on Lava lamp v1, xhigh effort, 18.11.2026 00:22 (run 4716ed3f)
Desktop · 1443.5 KB · ec38c4ef5a03…
Phone capture of Codex CLI (GPT-6.2 Astra)'s output on Lava lamp v1, xhigh effort, 18.11.2026 00:22 (run 4716ed3f)
Phone · 471.8 KB · 6504f6ca3485…
Motion capture of Codex CLI (GPT-6.2 Astra)'s output on Lava lamp v1, xhigh effort, 18.11.2026 00:22 (run 4716ed3f)
Motion · 1442.9 KB · 72535d1e1db6…

Along the row

GPT-6.2 Astra at every effort.

  1. GPT-6.2 Astra at low effort: desktop capture of run 58a9b80a Low3m 54s

    Works

    1 run
  2. GPT-6.2 Astra at medium effort: desktop capture of run 136194bc Medium9m 42s

    Works

    1 run
  3. GPT-6.2 Astra at high effort: desktop capture of run 6b64fc54 High9m 43s

    Works

    1 run
  4. GPT-6.2 Astra at extra high effort: desktop capture of run 4716ed3f Extra high15m 14s

    Works

    This effort
  5. MaxNot run

Down the column

Other models at extra high effort.

Fastest median first · this run: 15m 14s

  1. Muse Ember at extra high effort: desktop capture of run 8970cfdfMuse Ember52.1 s

    Works

    17.6× faster than this run
  2. GPT-6.1 Terra at extra high effort: desktop capture of run 3ae8f53fGPT-6.1 Terra1m 15s

    Works

    12.2× faster than this run
  3. GPT-5.6 Luna at extra high effort: desktop capture of run c312c80fGPT-5.6 Luna1m 25s

    Works

    10.8× faster than this run
  4. GPT-5.6 Terra at extra high effort: desktop capture of run 7eac2b69GPT-5.6 Terra3m 50s

    Works

    4.0× faster than this run
  5. GPT-5.6 Sol at extra high effort: desktop capture of run 0e1f62c1GPT-5.6 Sol4m 05s

    Fails

    3.7× faster than this run
  6. GPT-6 Luna at extra high effort: desktop capture of run 61c1a78eGPT-6 Luna4m 24s

    Works

    3.5× faster than this run
  7. GPT-6 Sol at extra high effort: desktop capture of run 10bc68ffGPT-6 Sol7m 11s

    Works

    2.1× faster than this run
  8. Claude Haiku 5.5 at extra high effort: desktop capture of run 90ef705aClaude Haiku 5.58m 28s

    Works

    1.8× faster than this run
  9. GPT-6.1 Sol at extra high effort: desktop capture of run 0b6358d6GPT-6.1 Sol11m 37s

    Works

    1.3× faster than this run
  10. GPT-6.2 Sol at extra high effort: desktop capture of run 9a6843d2GPT-6.2 Sol16m 03s

    Works

    1.1× slower than this run
  11. Qwen3.8 27B at extra high effort: desktop capture of run c5946c9bQwen3.8 27B20m 19s

    Works

    1.3× slower than this run
  12. Claude Sonnet 5.5 at extra high effort: desktop capture of run a46b8eabClaude Sonnet 5.521m 18s

    Works

    1.4× slower than this run
  13. GPT-6 Astra at extra high effort: desktop capture of run 47bb0692GPT-6 Astra25m 55s

    Works

    1.7× slower than this run
  14. Claude Opus 5.5 at extra high effort: desktop capture of run 499f4389Claude Opus 5.528m 09s

    Works

    1.8× slower than this run
  15. Claude Fable 5.1 at extra high effort: desktop capture of run bcfef55bClaude Fable 5.132m 58s

    Works

    2.2× slower than this run
  16. Claude Fable 5.2 at extra high effort: desktop capture of run e47eb2feClaude Fable 5.240m 03s

    Works

    2.6× slower than this run

Hidden checks

8 of 8 checks passed.

  • Self-contained index.html is presentblocker
  • Visible page contentblocker
  • Visible autonomous animationblocker
  • Accessible on/off controlextra
  • 390 px mobile layout has no horizontal overflowextra
  • Local animation frame performanceextra
  • No browser errorsblocker
  • No attempted external or linked-resource requestsblocker

It works when every blocker passes. How it looks is reviewed blind: pending.

Run detailsagent config, what ran, tokens, source and revisions
  • Video (video): not published, videos are withheld. SHA-256 f013a3ba72dbd02f8ba5c436e442a506baf6853099465cebfbd960ec49a223b1, 1940.8 KB.
Run ID
4716ed3f-f5f2-4839-a9ef-e209ba506a82
Benchmark
lava-lamp v1
Experiment
Single run
Started
18.11.2026 00:22 Tallinn
Graded
revision 1 · 18.11.2026 00:38

Works and checks, in full

All 5 blocker checks passed.

The rule: a run works when every blocker check passes. If any blocker fails it does not work. If none fails but one has no result yet, it stays pending, never counted as a pass or a fail. Extra checks are reported but do not decide it. Works is not a judgement of looks: that is the visual review.

This is a legacy contract v1 run: the task has no public requirements, and these are the original lava-lamp checks, not a versioned hidden verifier. It is never compared with contract v2 runs.

Contract v1 checks for this run, with blocker and result
RequirementCheckBlockerResult
none (v1)Self-contained index.html is presentBlockerpass
none (v1)Visible page contentBlockerpass
none (v1)Visible autonomous animationBlockerpass
none (v1)Accessible on/off controlExtrapass
none (v1)390 px mobile layout has no horizontal overflowExtrapass
none (v1)Local animation frame performanceExtrapass
none (v1)No browser errorsBlockerpass
none (v1)No attempted external or linked-resource requestsBlockerpass

Verification completed; eligible for benchmark results.

Visual review

Pending.

Pending: the captures have not been reviewed blind yet. Checks decide whether it works; how it looks is decided only in that review.

What ran

Requested and detected.

Detected values come from the run’s own output, never from our settings.

Requested agent config beside what the run reported
FieldRequestedDetectedEvidence
Modelgpt-6.2-astranot reportedThe harness reported no model.
Effortxhighnot reportedThe harness reported no effort; the requested effort is shown.
Harnessnot recordedcodex-cli 0.169.0Version as the CLI reported it; binary SHA-256 739cda86e15d…
Deadline60 min16m 13s usedCompleted

Tool decisions

35 calls · 35 without a decision

The harness reports no permission decision for its tool calls; the result of each call is still recorded.

  • command_execution33 calls · 4 failed
  • file_change2 calls

Telemetry

Time and usage.

Generation time
15m 14s
First content
4.4 s
Output speed
37.0 tokens/s, whole run including tools
API-equivalent cost
$2.37 (computed from the run’s token counts at list prices, not a charge)
Actual charge
not reported

Input tokens

1,243,842 tokens
  • Cache reads1,175,04094%
  • Cache writesnot reported
  • Uncached input68,8025.5%

Output tokens

33,774 tokens
  • Output33,774100%
  • Reasoningnot reported

Usage as the agent reported it at the end of the run. Cache reads are part of input; reasoning is part of output.

Transcript and source

Plain-text downloads.

The redacted transcript and the frozen output bundle, with LF line endings. Hashes are of the original files.

Redacted agent transcript: 52.3 KB, 0 redactions. Download transcript.txt

Source files

1 file · 32.1 KB
Files in the output bundle
FileSizeSHA-256Redactions
index.html32.1 KB9d92fc7b5284f5ca1a9c8602366a00e438c8f068f156ceb2da3589d1ae9963980
Bundle SHA-256 9d92fc7b5284f5ca1a9c8602366a00e438c8f068f156ceb2da3589d1ae996398

Revision history

This page shows revision 1.

Grades are append-only: a regrade adds a revision and never rewrites an earlier one.

Grading revisions of this run
RevisionGradedWorks
1 (current)18.11.2026 00:38works

Redaction: automated scan run; checked by Jaanus on 18.11.2026 00:42. Nothing needed redacting.