Lava lamp v1 · OpenCode · run 44255a11 · 09.11.2026 21:19 Tallinn

Muse Ember

Medium effort

Works

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

What it built: 3 captures

Desktop capture of OpenCode (Muse Ember)'s output on Lava lamp v1, medium effort, 09.11.2026 21:19 (run 44255a11)
Desktop · 518.3 KB · a48521198059…
Phone capture of OpenCode (Muse Ember)'s output on Lava lamp v1, medium effort, 09.11.2026 21:19 (run 44255a11)
Phone · 224.5 KB · f419978a53ff…
Motion capture of OpenCode (Muse Ember)'s output on Lava lamp v1, medium effort, 09.11.2026 21:19 (run 44255a11)
Motion · 534.7 KB · 3a3da49b79dd…

Along the row

Muse Ember at every effort.

  1. Muse Ember at low effort: desktop capture of run 9819d391 Low23.2 s

    Works

    1 run
  2. Muse Ember at medium effort: desktop capture of run 44255a11 Medium32.2 s

    Works

    This effort
  3. Muse Ember at high effort: desktop capture of run 9f5b66e4 High28.0 s

    Works

    1 run
  4. Muse Ember at extra high effort: desktop capture of run 8970cfdf Extra high52.1 s

    Works

    1 run
  5. Muse Ember at max effort: desktop capture of run 9f441dc8 Max47.7 s

    Works

    1 run

Down the column

Other models at medium effort.

Fastest median first · this run: 32.2 s

  1. GPT-6.1 Terra at medium effort: desktop capture of run f2424202GPT-6.1 Terra47.9 s

    Works

    1.5× slower than this run
  2. GPT-5.6 Luna at medium effort: desktop capture of run 69d0eb8eGPT-5.6 Luna59.1 s

    Works

    1.8× slower than this run
  3. GPT-6 Luna at medium effort: desktop capture of run 0e2e690dGPT-6 Luna1m 21s

    Works

    2.5× slower than this run
  4. GPT-5.6 Terra at medium effort: desktop capture of run 69024137GPT-5.6 Terra1m 48s

    Works

    3.4× slower than this run
  5. GPT-5.6 Sol at medium effort: desktop capture of run d3591876GPT-5.6 Sol2m 20s

    Fails

    4.4× slower than this run
  6. GPT-6 Astra at medium effort: desktop capture of run d0b2c47fGPT-6 Astra4m 15s

    Works

    7.9× slower than this run
  7. Claude Sonnet 5.5 at medium effort: desktop capture of run 2152d2b4Claude Sonnet 5.54m 44s

    Works

    8.8× slower than this run
  8. GPT-6.1 Sol at medium effort: desktop capture of run 0d942441GPT-6.1 Sol4m 52s

    Works

    9.0× slower than this run
  9. Claude Fable 5.1 at medium effort: desktop capture of run 6d90c6ceClaude Fable 5.14m 53s

    Works

    9.1× slower than this run
  10. Claude Haiku 5.5 at medium effort: desktop capture of run 012cc119Claude Haiku 5.55m 06s

    Works

    9.5× slower than this run
  11. GPT-6.2 Sol at medium effort: desktop capture of run 992d5562GPT-6.2 Sol7m 02s

    Works

    13.1× slower than this run
  12. Claude Fable 5.2 at medium effort: desktop capture of run b79ff6d9Claude Fable 5.27m 47s

    Works

    14.5× slower than this run
  13. Claude Opus 5.5 at medium effort: desktop capture of run 483f29b0Claude Opus 5.58m 56s

    Works

    16.6× slower than this run
  14. GPT-6.2 Astra at medium effort: desktop capture of run 136194bcGPT-6.2 Astra9m 42s

    Works

    18.1× slower than this run
  15. GPT-6 Sol at medium effort: desktop capture of run 18de4544GPT-6 Sol—

    Works

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 f6c4a61f8952e5b4a73fc681746da5b98c9d23a0ec0ff99a56195e8808819cf8, 1013.5 KB.
Run ID
44255a11-4f64-463a-8020-b124af021fcd
Benchmark
lava-lamp v1
Experiment
Single run
Started
09.11.2026 21:19 Tallinn
Graded
revision 1 · 09.11.2026 21:20

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.

This run could use only file tools (read, write, edit, glob, grep): no shell.

Requested agent config beside what the run reported
FieldRequestedDetectedEvidence
Modelmeta/muse-embernot reportedThe harness reported no model.
Effortmediumnot reportedThe harness reported no effort; the requested effort is shown.
HarnessOpenCodeopencode v2.2.6Version as the CLI reported it; binary SHA-256 90e4d03597b0…
Deadline60 min1m 30s usedCompleted

Tool decisions

6 calls · 6 accepted · 0 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.

  • edit2 calls · 2 accepted
  • read2 calls · 2 accepted
  • grep1 call · 1 accepted
  • write1 call · 1 accepted

Telemetry

Time and usage.

Generation time
32.2 s
First content
2.2 s
Output speed
439.9 tokens/s, whole run including tools
API-equivalent cost
$0.01 (computed from the run’s token counts at list prices, not a charge)
Actual charge
not reported

Input tokens

119,511 tokens
  • Cache reads91,96077%
  • Cache writes00%
  • Uncached input27,55123%

Output tokens

14,177 tokens
  • Reasoning4,22830%
  • Other output9,94970%

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: 3.0 KB, 0 redactions. Download transcript.txt

Source files

1 file · 24.3 KB
Files in the output bundle
FileSizeSHA-256Redactions
index.html24.3 KB4570252dbcbe40f48d6e92d703085c73784fbbd6e83faa5c65771f4aed7a620c0
Bundle SHA-256 4570252dbcbe40f48d6e92d703085c73784fbbd6e83faa5c65771f4aed7a620c

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 21:20works

Redaction: automated scan run; checked by Jaanus on 09.11.2026 22:10. Nothing needed redacting.