Lava lamp v1 · Antigravity CLI19.11.2026 03:49
Gemini 4 Neon
Medium effortWorks
8 of 8 checks passed. All 5 required checks passed.
What it built
Build time
7m 55s
15th fastest of 17 models at medium effort.
Output tokens
46,912
15th fewest of 17 models at medium effort.
Output speed
99 tok/s
8th highest of 16 models at medium effort.
API cost
$1.06
Computed from the run’s token counts at list prices, not a charge.
Same model
Gemini 4 Neon at every effort.
Scroll sideways for all 4
Same effort
Other models at medium effort.
Fastest first. This run took 7m 55s.
Scroll sideways for all 17
Muse Ember32.2 sWorks
14.8× faster than this run
GPT-6.1 Terra47.9 sWorks
9.9× faster than this run
GPT-5.6 Luna59.1 sWorks
8.1× faster than this run
GPT-6 Luna1m 21sWorks
5.9× faster than this run
GPT-5.6 Terra1m 48sWorks
4.4× faster than this run
GPT-5.6 Sol2m 20sFails
3.4× faster than this run
GPT-6 Astra4m 15sWorks
1.9× faster than this run
Claude Sonnet 5.54m 44sWorks
1.7× faster than this run
GPT-6.1 Sol4m 52sWorks
1.6× faster than this run
Claude Fable 5.14m 53sWorks
1.6× faster than this run
Claude Haiku 5.55m 06sWorks
1.6× faster than this run
Inkling 2 Mini6m 50sWorks
1.2× faster than this run
GPT-6.2 Sol7m 02sWorks
1.1× faster than this run
Claude Fable 5.27m 47sWorks
about the same
Claude Opus 5.58m 56sWorks
1.1× slower than this run
GPT-6.2 Astra9m 42sWorks
1.2× slower than this run
GPT-6 SolWorks
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
- Antigravity CLI
- Model
- Gemini 4 Neon
- Effort
- Medium
- Build time
- 7m 55s
- Start to finish
- 8m 54s
- Input tokens
- 772,368 (689,210 from cache)
- Output tokens
- 46,912 (11,769 reasoning)
- API cost
- $1.06, computed from token counts at list prices
Full record (run.json) Every check, hash, version and revision, as published.


