Lava lamp v1 · OpenCode · run c5946c9b · 11.11.2026 06:18 Tallinn
Qwen3.8 27B
Extra high effortWorks
7 of 8 checks passed. All 5 blocker checks passed.
What it built: 3 captures
Build time
20m 19s
12th fastest of 17 models at extra high effort. Wall time, start to graded: 21m 17s.
Output tokens
42,471
11th fewest of 17 models at extra high effort.
Output speed
35 tok/s
15th highest of 17 models at extra high effort.
API cost
None
The model ran on our own GPU: no API, so no cost.
Along the row
Qwen3.8 27B at every effort.
- LowNot run
- MediumNot run
- HighNot run
Extra high20m 19sWorks
This effort- MaxNot run
Down the column
Other models at extra high effort.
Fastest median first · this run: 20m 19s
Muse Ember52.1 sWorks
23.4× faster than this run
GPT-6.1 Terra1m 15sWorks
16.3× faster than this run
GPT-5.6 Luna1m 25sWorks
14.4× faster than this run
GPT-5.6 Terra3m 50sWorks
5.3× faster than this run
GPT-5.6 Sol4m 05sFails
5.0× faster than this run
GPT-6 Luna4m 24sWorks
4.6× faster than this run
GPT-6 Sol7m 11sWorks
2.8× faster than this run
Claude Haiku 5.58m 28sWorks
2.4× faster than this run
GPT-6.1 Sol11m 37sWorks
1.7× faster than this run
GPT-6.2 Astra15m 14sWorks
1.3× faster than this run
GPT-6.2 Sol16m 03sWorks
1.3× faster than this run
Claude Sonnet 5.521m 18sWorks
about the same
GPT-6 Astra25m 55sWorks
1.3× slower than this run
Claude Opus 5.528m 09sWorks
1.4× slower than this run
Claude Fable 5.132m 58sWorks
1.6× slower than this run
Claude Fable 5.240m 03sWorks
2.0× slower than this run
Hidden checks
7 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 0f952a76958b35202df899b668241e671d3d7673ef4ba1d38a2e756682c96e44, 1511.4 KB.
- Run ID
- c5946c9b-21bd-4c70-9e62-61edc6f7706f
- Benchmark
- lava-lamp v1
- Experiment
- Single run
- Started
- 11.11.2026 06:18 Tallinn
- Graded
- revision 1 · 11.11.2026 06:39
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 | fail |
| 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.
Ran locally, every layer on one NVIDIA GeForce RTX 3090 24 GB: Qwen3.8-27B-UD-Q4_K_M.gguf from unsloth/Qwen3.8-27B-GGUF (Q4_K_M) in llama.cpp llama-server 0.9.0-dev (commit 494d0f4), with a 131,072-token context. No API, so no cost.
| Field | Requested | Detected | Evidence |
|---|---|---|---|
| Model | qwen/qwen3.8-27b | qwen3.8-27b (differs from the request) | harness result, 7 of 7 API requests |
| Effort | xhigh | xhigh | 7 of 7 API requests |
| Harness | OpenCode | opencode v2.2.7 | Version as the CLI reported it; binary SHA-256 b9d576000191… |
| Deadline | 60 min | 21m 17s 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.
- edit3 calls · 3 accepted
- read1 call · 1 accepted
- write1 call · 1 accepted
Telemetry
Time and usage.
- Generation time
- 20m 19s
- First content
- 16m 28s
- Output speed
- 34.8 tokens/s, whole run including tools
- API-equivalent cost
- none, local model (no API)
- Actual charge
- not reported
Input tokens
- Cache reads204,32982%
- Cache writesnot reported
- Uncached input43,86418%
Output tokens
- Output42,471100%
- 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: 3.2 KB, 0 redactions. Download transcript.txt
Source files
| File | Size | SHA-256 | Redactions |
|---|---|---|---|
| index.html | 17.2 KB | ed83eb4b06ad6d543676e0e19bb484e77481ade9083b14a46874553265c0e598 | 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) | 11.11.2026 06:39 | works |
Redaction: automated scan run; checked by Jaanus on 11.11.2026 06:43. Nothing needed redacting.


