Lava lamp v1 · OpenCode · run 9f5b66e4 · 09.11.2026 21:20 Tallinn
Muse Ember
High effortWorks
8 of 8 checks passed. All 5 blocker checks passed.
What it built: 3 captures
Build time
28.0 s
Fastest of 16 models at high effort. Wall time, start to graded: 1m 26s.
Output tokens
11,539
7th fewest of 16 models at high effort.
Output speed
412 tok/s
Highest of 16 models at high effort.
API cost
$0.0076
Computed from the run’s token counts at list prices, not a charge.
Along the row
Muse Ember at every effort.
Down the column
Other models at high effort.
Fastest median first · this run: 28.0 s
GPT-5.6 Terra1m 00sWorks
2.1× slower than this run
GPT-5.6 Luna1m 04sWorks
2.3× slower than this run
GPT-6.1 Terra1m 12sWorks
2.6× slower than this run
GPT-6 Luna1m 27sWorks
3.1× slower than this run
GPT-5.6 Sol2m 34sWorks
5.5× slower than this run
GPT-6 Sol4m 12sWorks
9.0× slower than this run
GPT-6.1 Sol5m 15sWorks
11.2× slower than this run
Claude Haiku 5.55m 22sWorks
11.5× slower than this run
Claude Sonnet 5.56m 45sWorks
14.5× slower than this run
GPT-6 Astra7m 30sWorks
16.1× slower than this run
GPT-6.2 Astra9m 43sWorks
20.8× slower than this run
GPT-6.2 Sol11m 10sWorks
23.9× slower than this run
Claude Opus 5.513m 48sWorks
29.6× slower than this run
Claude Fable 5.114m 06sWorks
30.2× slower than this run
Claude Fable 5.234m 55sWorks
74.8× 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 details
- Video (video): not published, videos are withheld. SHA-256 8aed189788ff4f89952b059a787735667f6243584cee2751b00460da12b34870, 2016.4 KB.
- Run ID
- 9f5b66e4-4a22-4bcd-aa37-8404692707a6
- Benchmark
- lava-lamp v1
- Experiment
- Single run
- Started
- 09.11.2026 21:20 Tallinn
- Graded
- revision 1 · 09.11.2026 21:22
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.
| Requirement | Check | Blocker | Result |
|---|---|---|---|
| none (v1) | Self-contained index.html is present | Blocker | pass |
| none (v1) | Visible page content | Blocker | pass |
| none (v1) | Visible autonomous animation | Blocker | pass |
| none (v1) | Accessible on/off control | Extra | pass |
| none (v1) | 390 px mobile layout has no horizontal overflow | Extra | pass |
| none (v1) | Local animation frame performance | Extra | pass |
| none (v1) | No browser errors | Blocker | pass |
| none (v1) | No attempted external or linked-resource requests | Blocker | pass |
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.
| Field | Requested | Detected | Evidence |
|---|---|---|---|
| Model | meta/muse-ember | not reported | The harness reported no model. |
| Effort | high | not reported | The harness reported no effort; the requested effort is shown. |
| Harness | OpenCode | opencode v2.2.6 | Version as the CLI reported it; binary SHA-256 90e4d03597b0… |
| Deadline | 60 min | 1m 26s used | Completed |
Tool decisions
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
- write1 call · 1 accepted
Telemetry
Time and usage.
- Generation time
- 28.0 s
- First content
- 2.1 s
- Output speed
- 412.0 tokens/s, whole run including tools
- API-equivalent cost
- $0.0076 (computed from the run’s token counts at list prices, not a charge)
- Actual charge
- not reported
Input tokens
- Cache reads77,22883%
- Cache writes00%
- Uncached input15,53417%
Output tokens
- Reasoning4,24437%
- Other output7,29563%
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: 3.1 KB, 0 redactions. Download transcript.txt
Source files
| File | Size | SHA-256 | Redactions |
|---|---|---|---|
| index.html | 16.5 KB | 4bea5d2872c281376ff17bfd86b66bf48458fb38bc5b5acf9aa6293cfd12b535 | 0 |
Revision history
This page shows revision 1.
Grades are append-only: a regrade adds a revision and never rewrites an earlier one.
| Revision | Graded | Works |
|---|---|---|
| 1 (current) | 09.11.2026 21:22 | works |
Redaction: automated scan run; checked by Jaanus on 09.11.2026 22:10. Nothing needed redacting.


