Lava lamp v1 · Antigravity CLI19.11.2026 03:57
Gemini 4 Neon
High effortWorks
8 of 8 checks passed. All 5 required checks passed.
What it built
Build time
11m 56s
14th fastest of 18 models at high effort.
Output tokens
67,191
15th fewest of 18 models at high effort.
Output speed
94 tok/s
8th highest of 18 models at high effort.
API cost
$1.77
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 high effort.
Fastest first. This run took 11m 56s.
Scroll sideways for all 17
Muse Ember28.0 sWorks
25.6× faster than this run
GPT-5.6 Terra1m 00sWorks
11.9× faster than this run
GPT-5.6 Luna1m 04sWorks
11.1× faster than this run
GPT-6.1 Terra1m 12sWorks
9.9× faster than this run
GPT-6 Luna1m 27sWorks
8.2× faster than this run
GPT-5.6 Sol2m 34sWorks
4.7× faster than this run
GPT-6 Sol4m 12sWorks
2.8× faster than this run
GPT-6.1 Sol5m 15sWorks
2.3× faster than this run
Claude Haiku 5.55m 22sWorks
2.2× faster than this run
Claude Sonnet 5.56m 45sWorks
1.8× faster than this run
GPT-6 Astra7m 30sWorks
1.6× faster than this run
GPT-6.2 Astra9m 43sWorks
1.2× faster than this run
GPT-6.2 Sol11m 10sWorks
1.1× faster than this run
Claude Opus 5.513m 48sWorks
1.2× slower than this run
Claude Fable 5.114m 06sWorks
1.2× slower than this run
Inkling 2 Mini22m 39sWorks
1.9× slower than this run
Claude Fable 5.234m 55sWorks
2.9× 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
- Antigravity CLI
- Model
- Gemini 4 Neon
- Effort
- High
- Build time
- 11m 56s
- Start to finish
- 12m 55s
- Input tokens
- 1,580,643 (1,396,702 from cache)
- Output tokens
- 67,191 (25,171 reasoning)
- API cost
- $1.77, computed from token counts at list prices
Full record (run.json) Every check, hash, version and revision, as published.


