Lava lamp v1 · OpenCode · run 9f441dc8 · 09.11.2026 21:24 Tallinn

Muse Ember

Max 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, max effort, 09.11.2026 21:24 (run 9f441dc8)
Desktop · 560.5 KB · 5fd593260b4d…
Phone capture of OpenCode (Muse Ember)'s output on Lava lamp v1, max effort, 09.11.2026 21:24 (run 9f441dc8)
Phone · 246.6 KB · b41811f423c2…
Motion capture of OpenCode (Muse Ember)'s output on Lava lamp v1, max effort, 09.11.2026 21:24 (run 9f441dc8)
Motion · 556.9 KB · c7050007e753…

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

    1 run
  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

    This effort

Down the column

Other models at max effort.

Fastest median first · this run: 47.7 s

  1. GPT-5.6 Luna at max effort: desktop capture of run ab2b3d6aGPT-5.6 Luna2m 22s

    Works

    3.0× slower than this run
  2. GPT-5.6 Terra at max effort: desktop capture of run f8748487GPT-5.6 Terra4m 04s

    Fails

    5.1× slower than this run
  3. GPT-6 Luna at max effort: desktop capture of run 8dee2af3GPT-6 Luna4m 38s

    Works

    5.8× slower than this run
  4. GPT-6.1 Terra at max effort: desktop capture of run f1cd6f87GPT-6.1 Terra4m 55s

    Works

    6.2× slower than this run
  5. GPT-5.6 Sol at max effort: desktop capture of run 5a62dd4eGPT-5.6 Sol7m 53s

    Fails

    9.9× slower than this run
  6. GPT-6 Sol at max effort: desktop capture of run f796ca14GPT-6 Sol13m 48s

    Works

    17.4× slower than this run
  7. GPT-6.1 Sol at max effort: desktop capture of run aa82c8e5GPT-6.1 Sol16m 56s

    Works

    21.3× slower than this run
  8. Claude Haiku 5.5 at max effort: desktop capture of run 7250efd0Claude Haiku 5.520m 00s

    Works

    25.2× slower than this run
  9. GPT-6 Astra at max effort: desktop capture of run 9b8c977cGPT-6 Astra36m 32s

    Works

    46.0× slower than this run
  10. Claude Fable 5.1 at max effort: desktop capture of run 1d1e1f7fClaude Fable 5.136m 52s

    Works

    46.4× slower than this run
  11. Claude Opus 5.5 at max effort: desktop capture of run e684fb53Claude Opus 5.566m 39s

    Works

    83.9× slower than this run
  12. Claude Sonnet 5.5 at max effort: desktop capture of run 42c0200cClaude Sonnet 5.587m 03s

    Works

    109.6× 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 eb256110c5f0fbc33ddf9738bacadad98f3190f7034d348f883cad61738d008b, 2217.6 KB.
Run ID
9f441dc8-30c4-453b-9723-5984a6e70b6b
Benchmark
lava-lamp v1
Experiment
Single run
Started
09.11.2026 21:24 Tallinn
Graded
revision 1 · 09.11.2026 21:25

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.
Effortmaxnot 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 46s usedCompleted

Tool decisions

9 calls · 9 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.

  • grep3 calls · 3 accepted
  • edit2 calls · 2 accepted
  • read2 calls · 2 accepted
  • glob1 call · 1 accepted
  • write1 call · 1 accepted

Telemetry

Time and usage.

Generation time
47.7 s
First content
1.9 s
Output speed
433.4 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

163,608 tokens
  • Cache reads130,73280%
  • Cache writes00%
  • Uncached input32,87620%

Output tokens

20,652 tokens
  • Reasoning11,27955%
  • Other output9,37345%

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 · 22.3 KB
Files in the output bundle
FileSizeSHA-256Redactions
index.html22.3 KBad6dac46417817850fe99390a4517d6ff3f6da1ac9cc8b221226b2506d2541750
Bundle SHA-256 ad6dac46417817850fe99390a4517d6ff3f6da1ac9cc8b221226b2506d254175

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 21:25works

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