Lava lamp v1 · Codex CLI · run 4a1042d5 · 17.11.2026 23:15 Tallinn

GPT-6.2 Sol

Low 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 Sol)'s output on Lava lamp v1, low effort, 17.11.2026 23:15 (run 4a1042d5)
Desktop · 467.9 KB · 1d7613811fde…
Phone capture of Codex CLI (GPT-6.2 Sol)'s output on Lava lamp v1, low effort, 17.11.2026 23:15 (run 4a1042d5)
Phone · 152.8 KB · 841a2106835d…
Motion capture of Codex CLI (GPT-6.2 Sol)'s output on Lava lamp v1, low effort, 17.11.2026 23:15 (run 4a1042d5)
Motion · 466.6 KB · a8cdd0218190…

Along the row

GPT-6.2 Sol at every effort.

  1. GPT-6.2 Sol at low effort: desktop capture of run 4a1042d5 Low2m 56s

    Works

    This effort
  2. GPT-6.2 Sol at medium effort: desktop capture of run 992d5562 Medium7m 02s

    Works

    1 run
  3. GPT-6.2 Sol at high effort: desktop capture of run cc6c59e3 High11m 10s

    Works

    1 run
  4. GPT-6.2 Sol at extra high effort: desktop capture of run 9a6843d2 Extra high16m 03s

    Works

    1 run
  5. MaxNot run

Down the column

Other models at low effort.

Fastest median first · this run: 2m 56s

  1. Muse Ember at low effort: desktop capture of run 9819d391Muse Ember23.2 s

    Works

    7.6× faster than this run
  2. GPT-5.6 Luna at low effort: desktop capture of run 4b99cb20GPT-5.6 Luna29.7 s

    Works

    5.9× faster than this run
  3. GPT-6.1 Terra at low effort: desktop capture of run e58b2b0cGPT-6.1 Terra42.9 s

    Works

    4.1× faster than this run
  4. GPT-6 Luna at low effort: desktop capture of run 46ad720eGPT-6 Luna51.5 s

    Fails

    3.4× faster than this run
  5. GPT-5.6 Terra at low effort: desktop capture of run 0512c0d4GPT-5.6 Terra1m 38s

    Works

    1.8× faster than this run
  6. Claude Opus 5.5 at low effort: desktop capture of run dc76fa3bClaude Opus 5.51m 42s

    Works

    1.7× faster than this run
  7. GPT-5.6 Sol at low effort: desktop capture of run 184f5448GPT-5.6 Sol1m 46s

    Works

    1.7× faster than this run
  8. Claude Haiku 5.5 at low effort: desktop capture of run 69b2dfe6Claude Haiku 5.52m 36s

    Works

    1.1× faster than this run
  9. Claude Sonnet 5.5 at low effort: desktop capture of run b7f9c96bClaude Sonnet 5.52m 37s

    Works

    1.1× faster than this run
  10. GPT-6 Sol at low effort: desktop capture of run 0beb33c6GPT-6 Sol2m 39s

    Works

    1.1× faster than this run
  11. Claude Fable 5.1 at low effort: desktop capture of run 4bd42367Claude Fable 5.12m 50s

    Works

    about the same
  12. GPT-6.1 Sol at low effort: desktop capture of run 80d2eb3dGPT-6.1 Sol3m 11s

    Works

    1.1× slower than this run
  13. GPT-6.2 Astra at low effort: desktop capture of run 58a9b80aGPT-6.2 Astra3m 54s

    Works

    1.3× slower than this run
  14. GPT-6 Astra at low effort: desktop capture of run e375a13dGPT-6 Astra4m 17s

    Works

    1.5× slower than this run
  15. Claude Fable 5.2 at low effort: desktop capture of run 96e988f7Claude Fable 5.24m 43s

    Works

    1.6× 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 ed7b6677a8918ba3a4f9020cc7425211fb6f036571e736c9c71c2a3e9cc2d20c, 1092.7 KB.
Run ID
4a1042d5-d1fb-4c49-9492-1fffc2753e8b
Benchmark
lava-lamp v1
Experiment
Single run
Started
17.11.2026 23:15 Tallinn
Graded
revision 1 · 17.11.2026 23:19

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-solnot reportedThe harness reported no model.
Effortlownot 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 min3m 55s usedCompleted

Tool decisions

3 calls · 3 without a decision

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

  • command_execution3 calls · 1 failed

Telemetry

Time and usage.

Generation time
2m 56s
First content
4.1 s
Output speed
46.1 tokens/s, whole run including tools
API-equivalent cost
$0.16 (computed from the run’s token counts at list prices, not a charge)
Actual charge
not reported

Input tokens

75,815 tokens
  • Cache reads40,57654%
  • Cache writesnot reported
  • Uncached input35,23946%

Output tokens

8,128 tokens
  • Output8,128100%
  • 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: 13.6 KB, 0 redactions. Download transcript.txt

Source files

1 file · 10.2 KB
Files in the output bundle
FileSizeSHA-256Redactions
index.html10.2 KB6ecddf26bdf6a6287268c32f08b3f293408ec49f36365dbdd65a2e5537891f090
Bundle SHA-256 6ecddf26bdf6a6287268c32f08b3f293408ec49f36365dbdd65a2e5537891f09

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)17.11.2026 23:19works

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