Lava lamp v1 · Claude Code · run e47eb2fe · 09.11.2026 21:11 Tallinn

Claude Fable 5.2

Extra high effort

Works

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

What it built: 3 captures

Desktop capture of Claude Code (Fable 5.2)'s output on Lava lamp v1, xhigh effort, 09.11.2026 21:11 (run e47eb2fe)
Desktop · 659.4 KB · 2e458b7cc7d4…
Phone capture of Claude Code (Fable 5.2)'s output on Lava lamp v1, xhigh effort, 09.11.2026 21:11 (run e47eb2fe)
Phone · 159.0 KB · ae185f93ec7a…
Motion capture of Claude Code (Fable 5.2)'s output on Lava lamp v1, xhigh effort, 09.11.2026 21:11 (run e47eb2fe)
Motion · 659.6 KB · 5e9acb3215b3…

Along the row

Claude Fable 5.2 at every effort.

  1. Claude Fable 5.2 at low effort: desktop capture of run 96e988f7 Low4m 43s

    Works

    1 run
  2. Claude Fable 5.2 at medium effort: desktop capture of run b79ff6d9 Medium7m 47s

    Works

    1 run
  3. Claude Fable 5.2 at high effort: desktop capture of run 45666ded High34m 55s

    Works

    1 run
  4. Claude Fable 5.2 at extra high effort: desktop capture of run e47eb2fe Extra high40m 03s

    Works

    This effort
  5. MaxNot run

Down the column

Other models at extra high effort.

Fastest median first · this run: 40m 03s

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

    Works

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

    Works

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

    Works

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

    Works

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

    Fails

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

    Works

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

    Works

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

    Works

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

    Works

    3.4× faster than this run
  10. GPT-6.2 Astra at extra high effort: desktop capture of run 4716ed3fGPT-6.2 Astra15m 14s

    Works

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

    Works

    2.5× faster than this run
  12. Qwen3.8 27B at extra high effort: desktop capture of run c5946c9bQwen3.8 27B20m 19s

    Works

    2.0× faster than this run
  13. Claude Sonnet 5.5 at extra high effort: desktop capture of run a46b8eabClaude Sonnet 5.521m 18s

    Works

    1.9× faster than this run
  14. GPT-6 Astra at extra high effort: desktop capture of run 47bb0692GPT-6 Astra25m 55s

    Works

    1.5× faster than this run
  15. Claude Opus 5.5 at extra high effort: desktop capture of run 499f4389Claude Opus 5.528m 09s

    Works

    1.4× faster than this run
  16. Claude Fable 5.1 at extra high effort: desktop capture of run bcfef55bClaude Fable 5.132m 58s

    Works

    1.2× faster 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 95ef2a27c3961352667ae32efe8417d30794b9cb7ffd6fd8658ff23c16401830, 1298.2 KB.
Run ID
e47eb2fe-9ca0-49a3-854a-cdb09ac70f48
Benchmark
lava-lamp v1
Experiment
Single run
Started
09.11.2026 21:11 Tallinn
Graded
revision 1 · 09.11.2026 21:52

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
Modelclaude-fable-5-2claude-fable-5-2harness result, 44 of 44 API requests
Effortxhighxhigh44 of 44 API requests
Harnessnot recorded2.1.319 (Claude Code)Version as the CLI reported it; binary SHA-256 1f53587e92de…
Deadline180 min41m 02s usedCompleted

Tool decisions

75 calls · 74 accepted · 1 rejected

Each tool call is allowed or blocked by the harness’s permission settings before it runs. Allowed is not the same as succeeded: an allowed call can still fail.

  • Edit32 calls · 32 accepted
  • Bash22 calls · 21 accepted · 1 rejected · 13 failed
  • Read10 calls · 10 accepted
  • Write8 calls · 8 accepted
  • Grep3 calls · 3 accepted

Telemetry

Time and usage.

Generation time
40m 03s
First content
1.1 s
Output speed
93.9 tokens/s, whole run including tools
API-equivalent cost
$13.08 (computed from the run’s token counts at list prices, not a charge)
Actual charge
not reported

Input tokens

3,594,014 tokens
  • Cache reads3,381,44194%
  • Cache writes210,3015.9%
  • Uncached input2,272<0.1%

Output tokens

225,641 tokens
  • Reasoning161,55072%
  • Other output64,09128%

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: 188.6 KB, 40 redactions. Download transcript.txt

Source files

1 file · 37.3 KB
Files in the output bundle
FileSizeSHA-256Redactions
index.html37.3 KB475e4ecf81ef53ab58d1408043cae9bbcfc9900492ac0f0c2121f5b0d38544850
Bundle SHA-256 475e4ecf81ef53ab58d1408043cae9bbcfc9900492ac0f0c2121f5b0d3854485

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)09.11.2026 21:52works

Redaction: automated scan run; checked by Jaanus on 09.11.2026 22:10. Redacted: 2 email, 23 local-path, 6 user-path, 9 username.