Lava lamp v1 · OpenCode21.11.2026 08:02
Inkling 2 Mini
Extra high effortWorks
8 of 8 checks passed. All 5 required checks passed.
What it built
Build time
16m 38s
12th fastest of 19 models at extra high effort.
Output tokens
44,641
13th fewest of 19 models at extra high effort.
API cost
None
The model ran on our own GPU: no API, so no cost.
Same model
Inkling 2 Mini at every effort.
Scroll sideways for all 4
Same effort
Other models at extra high effort.
Fastest first. This run took 16m 38s.
Scroll sideways for all 18
Muse Ember52.1 sWorks
19.2× faster than this run
GPT-6.1 Terra1m 15sWorks
13.3× faster than this run
GPT-5.6 Luna1m 25sWorks
11.8× faster than this run
GPT-5.6 Terra3m 50sWorks
4.3× faster than this run
GPT-5.6 Sol4m 05sFails
4.1× faster than this run
GPT-6 Luna4m 24sWorks
3.8× faster than this run
GPT-6 Sol7m 11sWorks
2.3× faster than this run
Claude Haiku 5.58m 28sWorks
2.0× faster than this run
GPT-6.1 Sol11m 37sWorks
1.4× faster than this run
GPT-6.2 Astra15m 14sWorks
1.1× faster than this run
GPT-6.2 Sol16m 03sWorks
about the same
Qwen3.8 27B20m 19sWorks
1.2× slower than this run
Claude Sonnet 5.521m 18sWorks
1.3× slower than this run
Gemini 4 Neon22m 26sWorks
1.3× slower than this run
GPT-6 Astra25m 55sWorks
1.6× slower than this run
Claude Opus 5.528m 09sWorks
1.7× slower than this run
Claude Fable 5.132m 58sWorks
2.0× slower than this run
Claude Fable 5.240m 03sWorks
2.4× slower than this run
Checks
8 of 8 checks passed.
- Self-contained index.html is presentRequired
- Visible page contentRequired
- Visible autonomous animationRequired
- Accessible on/off controlOptional
- 390 px mobile layout has no horizontal overflowOptional
- Local animation frame performanceOptional
- No browser errorsRequired
- No attempted external or linked-resource requestsRequired
It works when it passes every required check; optional checks are reported, but they don’t decide that.
Run details
- Agent
- OpenCode
- Model
- Inkling 2 Mini
- Effort
- Extra high
- Build time
- 16m 38s
- Start to finish
- 17m 37s
- First output
- 9m 26s
- Input tokens
- 624,526 (574,701 from cache)
- Output tokens
- 44,641
- API cost
- None: ran on one NVIDIA GeForce RTX 3090 24 GB
Full record (run.json) Every check, hash, version and revision, as published.


