ModelBrief · Gemini 4 Carbon · Topic Page
Last updated Nov 13, 2026

Huxiu's Nine Antigravity Tests: Nothing Failed — but Nothing Amazed Either

Published Nov 13, 2026 · Last updated Nov 13, 2026

On November 11, Huxiu published a long Chinese-language review of Carbon: nine tasks in Google Antigravity at High thinking, all one-shot, no human intervention. The headline translates as "Already hooked — Google quietly returns to the table." But read closely, the excitement is about stable delivery, not stunning output: nothing failed outright, and nothing reached top tier either.

The nine tests, one by one

TaskResultShortfall
Hong Kong "hairy crab" floor plan → walkable 3D buildingDone in ~1 hr; spatial relations correct; self-added furniture, stove, day-night cycleSimple furniture, repeated materials
iPhone Duo interactive 3D exhibit~40 min; exploded view, hinge demo, screen handoff tied to hinge angleScreen content poking out of the rounded body; poor internal lighting
Cloth physics: silk scroll~17 min; hand-written Verlet cloth with calligraphy; draggable, tearableHard angles on big pulls; unrealistic tearing
Frame-by-frame remake of a 20s Claude Opus promoIdentified 37 hard cuts matching the original; rhythm preservedRacehorse became vector art; lace became repeated flowers
8D Chongqing night scenePlayable; the light rail through the building was the highlightOverall a "low-spec version"
Pelican-on-bicycle SVGFlawless—
"The most beautiful webpage"Gorgeous cosmic themeFormulaic across repeated runs
"Bear shaking its fur" dance breakdownGood analysisFollow-along misaligned
15-second art history (bonus)First version looked greatIt "cheated" by calling image generation; the code-only redo was lower quality

The author's verdict: stable, but no longer chasing #1

The author's overall read is that Carbon "no longer slacks off" — every task was delivered, nothing stalled or gave up halfway, the clearest improvement over previous Google models. But the author also noticed a tell: Google no longer claims "strongest" and instead stresses a cost per task under half of #2's, at about a quarter of Fable 5.2's price. The timeline supports that reading: Carbon's AA index #1 lasted about two days (Nov 7–9) before Fable 5.2 passed it at 65 — a few days late, and the top spot was gone.

Yupi's test of the same Chongqing prompt points the same way: in Cursor, Carbon produced only 184 boxy buildings against Fable 5.2's 1,230, and Huxiu likewise called its Chongqing night scene a "low-spec version". Two independent Chinese tests converge on the same point: Carbon delivers, but finish and taste still trail Fable 5.2. See our write-up of Yupi's three front-end tasks.

Our take: Huxiu's nine tests are the friendliest Chinese-language review of Carbon — nine one-shot deliveries, zero failures, real evidence of its stability as a long-horizon agent. But there is still distance between "stable" and "top tier": finish, taste and physical realism all fall a little short. Carbon reads more like a reliable workhorse than a dazzling artist.

Reference source: this article is an original rewrite produced by this site; facts and figures were checked against Huxiu's nine Antigravity tests (Nov 11, 2026)

← Back to the Gemini 4 Carbon topic page