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

A reply notes Google also claims Gemini 4 Argon helped find the vulnerability, with everyone eager to take credit.

Researchers using GPT-5.6 Sol plus Gemini 4 Argon and human review found a PHP flaw letting unauthenticated attackers run code or read secrets.

Google says its Gemini 4 Argon model helped discover and mitigate critical security flaws in PHP, per multiple news accounts.

After Gemini 4 Argon's wider release, Google's CEO discusses early reception, where the model still needs work, DeepMind leadership changes, compute spending, and Gemini's personal agent plans.

PHP 8.2–8.5 patched two critical unauthenticated RCE and memory-leak flaws (CVE-2026-109618/109619), with Wiz saying Gemini 4 Argon and GPT-5.6 Sol strongly assisted the discovery.

A user had Gemini 4 Carbon generate a three.js mechanical flower in about 1h43m, including an unprompted bee, and calls it a clear improvement over Argon.

DeepMind had Argon watch a human play cornhole and produce MuJoCo simulation motions, letting Apptronik's Apollo sink seven straight real-world shots.

A Gemini 4 Carbon checkpoint spotted on Arena under the name "Gemini 4 Argon" renders an SVG of a pelican riding a bike through four seasons, shown in a video.

Wiz found two CVSS 9.2 PHP remote-code flaws affecting PHP 5.4+, using Gemini 4 Argon and GPT-5.6 Sol to help discover, test and verify fixes.

A reply to steipete says the team behind a discovery credits Gemini 4 Argon with doing the lion's share of the work amid others claiming credit.

The author splits a static city image into background, midground, and foreground depth plates to create a parallax animation, crediting Gemini 4 Argon for the technique and demo.

A roundup lists 10 examples of people building 3D worlds, robots and games with Gemini 4 Argon, framing it as Google's comeback.