Lava lamp v1 · OpenCode21.11.2026 07:38
Inkling 2 Mini
High effortWorks
7 of 8 checks passed. All 5 required checks passed.
What it built
Build time
22m 39s
17th fastest of 18 models at high effort.
Output tokens
60,775
13th fewest of 18 models at high effort.
Output speed
45 tok/s
16th highest of 18 models at 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 high effort.
Fastest first. This run took 22m 39s.
Scroll sideways for all 17
Muse Ember28.0 sWorks
48.5× faster than this run
GPT-5.6 Terra1m 00sWorks
22.7× faster than this run
GPT-5.6 Luna1m 04sWorks
21.1× faster than this run
GPT-6.1 Terra1m 12sWorks
18.9× faster than this run
GPT-6 Luna1m 27sWorks
15.5× faster than this run
GPT-5.6 Sol2m 34sWorks
8.8× faster than this run
GPT-6 Sol4m 12sWorks
5.4× faster than this run
GPT-6.1 Sol5m 15sWorks
4.3× faster than this run
Claude Haiku 5.55m 22sWorks
4.2× faster than this run
Claude Sonnet 5.56m 45sWorks
3.4× faster than this run
GPT-6 Astra7m 30sWorks
3.0× faster than this run
GPT-6.2 Astra9m 43sWorks
2.3× faster than this run
GPT-6.2 Sol11m 10sWorks
2.0× faster than this run
Gemini 4 Neon11m 56sWorks
1.9× faster than this run
Claude Opus 5.513m 48sWorks
1.6× faster than this run
Claude Fable 5.114m 06sWorks
1.6× faster than this run
Claude Fable 5.234m 55sWorks
1.5× slower than this run
Checks
7 of 8 checks passed.
- Accessible on/off controlNo on/off control a screen reader can find, or using it changed nothing.Optional
- Self-contained index.html is presentRequired
- Visible page contentRequired
- Visible autonomous animationRequired
- 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
- High
- Build time
- 22m 39s
- Start to finish
- 23m 38s
- First output
- 13m 33s
- Input tokens
- 1,134,907 (1,113,823 from cache)
- Output tokens
- 60,775
- API cost
- None: ran on one NVIDIA GeForce RTX 3090 24 GB
Full record (run.json) Every check, hash, version and revision, as published.


