Lava lamp v1 · Claude Code · run e47eb2fe · 09.11.2026 21:11 Tallinn
Claude Fable 5.2
Extra high effortWorks
8 of 8 checks passed. All 5 blocker checks passed.
What it built: 3 captures
Build time
40m 03s
17th fastest of 17 models at extra high effort. Wall time, start to graded: 41m 02s.
Output tokens
225,641
17th fewest of 17 models at extra high effort.
Output speed
94 tok/s
7th highest of 17 models at extra high effort.
API cost
$13.08
Computed from the run’s token counts at list prices, not a charge.
Along the row
Claude Fable 5.2 at every effort.
Down the column
Other models at extra high effort.
Fastest median first · this run: 40m 03s
Muse Ember52.1 sWorks
46.2× faster than this run
GPT-6.1 Terra1m 15sWorks
32.1× faster than this run
GPT-5.6 Luna1m 25sWorks
28.4× faster than this run
GPT-5.6 Terra3m 50sWorks
10.4× faster than this run
GPT-5.6 Sol4m 05sFails
9.8× faster than this run
GPT-6 Luna4m 24sWorks
9.1× faster than this run
GPT-6 Sol7m 11sWorks
5.6× faster than this run
Claude Haiku 5.58m 28sWorks
4.7× faster than this run
GPT-6.1 Sol11m 37sWorks
3.4× faster than this run
GPT-6.2 Astra15m 14sWorks
2.6× faster than this run
GPT-6.2 Sol16m 03sWorks
2.5× faster than this run
Qwen3.8 27B20m 19sWorks
2.0× faster than this run
Claude Sonnet 5.521m 18sWorks
1.9× faster than this run
GPT-6 Astra25m 55sWorks
1.5× faster than this run
Claude Opus 5.528m 09sWorks
1.4× faster than this run
Claude Fable 5.132m 58sWorks
1.2× faster 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 95ef2a27c3961352667ae32efe8417d30794b9cb7ffd6fd8658ff23c16401830, 1298.2 KB.
- Run ID
- e47eb2fe-9ca0-49a3-854a-cdb09ac70f48
- Benchmark
- lava-lamp v1
- Experiment
- Single run
- Started
- 09.11.2026 21:11 Tallinn
- Graded
- revision 1 · 09.11.2026 21:52
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-fable-5-2 | claude-fable-5-2 | harness result, 44 of 44 API requests |
| Effort | xhigh | xhigh | 44 of 44 API requests |
| Harness | not recorded | 2.1.319 (Claude Code) | Version as the CLI reported it; binary SHA-256 1f53587e92de… |
| Deadline | 180 min | 41m 02s 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.
- Edit32 calls · 32 accepted
- Bash22 calls · 21 accepted · 1 rejected · 13 failed
- Read10 calls · 10 accepted
- Write8 calls · 8 accepted
- Grep3 calls · 3 accepted
Telemetry
Time and usage.
- Generation time
- 40m 03s
- First content
- 1.1 s
- Output speed
- 93.9 tokens/s, whole run including tools
- API-equivalent cost
- $13.08 (computed from the run’s token counts at list prices, not a charge)
- Actual charge
- not reported
Input tokens
- Cache reads3,381,44194%
- Cache writes210,3015.9%
- Uncached input2,272<0.1%
Output tokens
- Reasoning161,55072%
- Other output64,09128%
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: 188.6 KB, 40 redactions. Download transcript.txt
Source files
| File | Size | SHA-256 | Redactions |
|---|---|---|---|
| index.html | 37.3 KB | 475e4ecf81ef53ab58d1408043cae9bbcfc9900492ac0f0c2121f5b0d3854485 | 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 21:52 | works |
Redaction: automated scan run; checked by Jaanus on 09.11.2026 22:10. Redacted: 2 email, 23 local-path, 6 user-path, 9 username.


