Lava lamp v1 · Claude Code · run 69b2dfe6 · 28.10.2026 07:44 Tallinn
Claude Haiku 5.5
Low effortWorks
8 of 8 checks passed. All 5 blocker checks passed.
What it built: 3 captures
Build time
2m 36s
7th fastest of 12 models at low effort. Wall time, start to graded: 3m 35s.
Output tokens
34,260
12th fewest of 12 models at low effort.
Output speed
220 tok/s
Highest of 12 models at low effort.
API cost
$0.02
The CLI’s list-price estimate, not a charge.
Along the row
Claude Haiku 5.5 at every effort.
Down the column
Other models at low effort.
Fastest median first · this run: 2m 36s
GPT-5.6 Luna29.7 sWorks
5.3× faster than this run
GPT-6.1 Terra42.9 sWorks
3.6× faster than this run
GPT-6 Luna51.5 sFails
3.0× faster than this run
GPT-5.6 Terra1m 38sWorks
1.6× faster than this run
Claude Opus 5.51m 42sWorks
1.5× faster than this run
GPT-5.6 Sol1m 46sWorks
1.5× faster than this run
Claude Sonnet 5.52m 37sWorks
about the same
GPT-6 Sol2m 39sWorks
about the same
Claude Fable 5.12m 50sWorks
1.1× slower than this run
GPT-6.1 Sol3m 11sWorks
1.2× slower than this run- No capture publishedGPT-6 Astra4m 17s
Not checked
1.6× 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 details
- Video (video): not published, videos are withheld. SHA-256 fe4303a46f977ed23df7046ec0424ed20b4b8969cadebcddf4fee0497d32dc4a, 1250.7 KB.
- Run ID
- 69b2dfe6-000f-43c5-af2f-4c3cdfb83948
- Benchmark
- lava-lamp v1
- Experiment
- Single run
- Started
- 28.10.2026 07:44 Tallinn
- Graded
- revision 1 · 28.10.2026 07:47
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.
| Field | Requested | Detected | Evidence |
|---|---|---|---|
| Model | claude-haiku-5-5 | claude-haiku-5-5 | harness result, 4 of 4 API requests |
| Effort | low | low | 4 of 4 API requests |
| Harness | not recorded | 2.1.312 (Claude Code) | Version as the CLI reported it; binary SHA-256 6b5ec691195e… |
| Deadline | 60 min | 3m 35s 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.
- Bash3 calls · 3 accepted · 3 failed
- Write1 call · 1 accepted
Telemetry
Time and usage.
- Generation time
- 2m 36s
- First content
- 1.7 s
- Output speed
- 219.7 tokens/s, whole run including tools
- API-equivalent cost
- $0.02 (list-price estimate, not a charge)
- Actual charge
- not reported
- Billing
- api
Input tokens
- Cache reads96,40069%
- Cache writes44,03231%
- Uncached input8<0.1%
Output tokens
- Reasoning26,73778%
- Other output7,52322%
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: 20.4 KB, 2 redactions. Download transcript.txt
Source files
| File | Size | SHA-256 | Redactions |
|---|---|---|---|
| index.html | 12.1 KB | 1bafd5fda39a1ac5971c5d74dd0427fd4f38b827713f34d4962446f8f5a20d37 | 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) | 28.10.2026 07:47 | works |
Redaction: automated scan run; checked by Jaanus on 28.10.2026 17:51. Redacted: 2 local-path.