Lavalamp
Lava Lamp — slow blob morph animation.
What I asked each model — the Lavalamp prompt
Every model on this page got this exact prompt inside the Agent Operating System: Lava Lamp — slow blob morph animation.
Single HTML file out. No iteration. No examples in the system prompt. Whatever each model produced on the first run is what's on this page. 23 frontier models have attempted it so far: Claude Fable 5, Fugu Ultra, Fugu Mini, Fusion, Gemini 3.6 Flash, GLM-5.2, GPT-5.6 Sol, Grok, Inkling, Kimi K3, MiniMax M3, Hermes MoA, Opus 4.8, Claude Opus 5, Qwen 3.8, Qwen 3.7, Claude Sonnet 5, Kimi K2.7 · Fast, Kimi K2.7 · No-Think, Kimi K2.7 · Quality, DeepSeek V4 Pro, DeepSeek V4 Flash, Kimi K2.7.
Why this task matters. Lavalamp is a textbook test of visual-class capability — the kind of build that exposes whether a model is doing pattern-matching or actual reasoning. Shipping this cleanly is the floor for what I expect from a frontier model — every model on the leaderboard should at least attempt it.
How each model handled Lavalamp
Ranked by my 0–10 score from the source comparison guides on agentos.guide. Click any to play the actual one-shot HTML the model produced.
What I saw: Strong metaball merging with convincing rim/glow and interactive stir/hue controls, but the blobs clumped into one oversized green mass filling most of the frame rather than distinct rising lava globs, hurting the classic lamp read.
What I saw: Ultra v2 — lava lamp. Smoke-test MAYBE (0.1% diff) — slow ambient motion is expected for this visual-only prompt.
What I saw: Mini gap-fill — lava lamp metaballs. Smoke-test PASS (0.7% diff).
What I saw: WebGL metaball shader with warm gradient. Smooth blob morphing, low-frequency motion. Simpler than the deep builds but on brief.
What I saw: Strong ambition with 3D lathe lamp geometry, raymarched blobs, glass material and theme switcher, but the render is largely dark/opaque — only two flat orange/red reservoir caps show with no visible mid-lamp blobs or morphing fluid, making it read as broken rather than a lively lava lamp.
What I saw: 6KB · plays clean · three, webgl, rAF
What I saw: Renders a polished full 3D lava lamp with glass vessel, metallic base/cap rings, morphing blobs and clean UI overlay — strong and shippable, but the blobs read washed-out/greyish rather than glowing lava colour, undercutting the signature vibrant morph feel.
What I saw: The capsule's full of bright gooey blobs now — cyan, pink and white metaballs rising and merging. The raymarched-shader version came up empty twice, so I had it rebuilt in plain Canvas 2D, and now it renders every time.
What I saw: Renders cleanly with warm glowing spheres and elegant typography, but the discrete shiny orbs read as floating balls rather than a true lava lamp — no metaball merging, no vertical rise/fall, and no glass vessel breaks the brief's core morph concept.
What I saw: Strong: a genuinely convincing lava lamp silhouette with glowing base, heated cap, warm wax gradient and a proper metaball shader plus polished typography and theme chips; minor weakness is the blob field looks a touch sparse/stratified in this frame, but the craft and shader detail clearly edge past the field's best.
The winner on Lavalamp
Claude Opus 5 took gold on this task. metaball lava lamp.
What I saw: Gorgeous shader metaball fluid with convincing tapered glass body, glowing gold cap and ribbed metal base, plus palette switching, heat slider and pointer interaction — clearly matches the field's best. Only nit: static screenshot can't confirm morph smoothness, but the blob variety and rim lighting are top-tier.
See Claude Opus 5's full model card: /models/opus5.
Every attempt — live, playable
Side by side. Click any tile to run that model's actual one-shot HTML in a new tab.
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVEHow I scored Lavalamp — methodology
Three axes, 0–10 each, averaged. Runs: drop the .html in a browser; if it opens to a broken page, it scores zero. Hits the brief: did the model ship the thing the prompt asked for, or a different thing it found easier. Looks good: visual polish, motion, interactivity — where most of the gap between gold and silver lives.
My scores trace back to the source comparison guides on agentos.guide. See the full methodology page for data provenance, including which source guide each cell's score came from.
Related
More visual benchmarks: all tasks in the Visual category · See the best AI model for Lavalamp · Back to the leaderboard
Run this stack yourself.
Every demo on this bench was built inside the Agent Operating System — one prompt, one shot, single HTML file out. The Agent OS, the prompts, the templates, the weekly walkthroughs and 4,000+ founders shipping with it every day all live inside the AI Profit Boardroom.