Gemini 4 Pro / Flash: benchmarks, hands-on tests and leaks

A Japanese post notes rumors that Gemini 4 Flash is about to launch, but complains that "coming soon" and "actually usable" are long seasons apart.

A user runs the same prompt once through Gemini 4 Argon's first checkpoint and Opus 5.5 high, showing a video comparison of the results.

The poster says Google AI Pro subscribers can use Gemini 4 Argon in the Gemini app, that Gemini 4 Carbon is coming soon, and highlights strong 3D, low cost and long context, plus a GamsGo promo.

Given the same prompt, Gemini 4 Argon and Claude Opus 5.5 each produced a white tiger prowling a palace, with fur, mist and lighting close to video-model quality.

A user shows Gemini 4 Argon generating raw SVG code for a pelican riding a bicycle, a quick probe of its vector-graphics output.

A developer notes that Gemini 4 Argon is accessible through the opencode Go subscription, calling frontier models cheaper than ever.

In an Arena test, Gemini 4 Carbon generated a neon restaurant scene in about 45 minutes, with results close to what Opus 5.5 produced.

A video runs the same lighthouse challenge across four models, showing Gemini 4 Argon at $6.30 versus Claude Sonnet 5.5 at $29.90, Opus 5.5 at $53.57 and GPT-6 Astra at $42.28.

A user says Gemini 4 Carbon turned a single 3D seaplane prompt into an infinite ocean with random island generation and driving controls, and calls it far stronger than Argon.

A reply asks whether Gemini 4 Flash is already at Sonnet 5.5 level, with no benchmark evidence offered.

A French post claims the new Gemini 4 checkpoint Carbon is much more powerful than Gemini 4 Argon and surpasses Opus 5.5 on 3D tasks.

MiniMax M3.1 Flash rose from 17% to 56% on AA Omniscience, passing Gemini 4 Argon; the author altered public questions and found the model still returned memorized answers, suggesting benchmark overfitting.