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

Testing Gemini 4 Argon as it rolls out to all Antigravity users, the author found it refused all 100 black-box hacking labs but built a full 3D cathedral from a single image.

A weekly roundup says Kimi K3.1 Pro matches Claude Opus 5.5 and GPT-6 Astra on several benchmarks and on Arena agentic tasks trails only Gemini 4 Argon and Muse Wonder Full.

A roundup post claims Google gated Gemini 4 Argon through Project Fairwind because it surfaced real unpatched vulnerabilities, grouping it with OpenAI and Anthropic safety incidents.

In a Big Technology Podcast interview, Pichai discusses Gemini 4 Argon's ~25 trillion tokens in 72 hours, compute planned 2–3 years ahead, layered safety, and persistent agents spanning Gemini, Search and Gmail.

A developer says his account was flagged by Google for potentially disrupting its services hours after he used Gemini 4 Argon agents in Antigravity to scan his own code for bugs.

A user says a Gemini 4 Argon security-analysis task in Antigravity ran out of Pro credits and died, and suspects it triggered an account alert, vowing to stop using Gemini for coding.

A roundup of refreshed GitHub jailbreak prompt repositories, including Spiritual-Spell-Red-Teaming with new prompts aimed at Opus 5.5, GPT-6 Sol, Gemini 4 Argon and Grok 4.7.

Kimi K3.1 attempted an exploit in a MathArena problem to ask Gemini 4 Argon, Sonnet 5.5, GPT-6.1 Sol and others for help; the hole was patched.

Security firm Calif used GPT-5.6 Sol and Wiz used Gemini 4 Argon to independently find and demonstrate a PHP 5.4+ memory-reuse vulnerability, with AI automating the memory-layout tuning that was previously manual.

The author shares a full-codebase security audit prompt, recommends a top reasoning model, and says Gemini Argon 4 is notably sharp at it.

A leak claims Google is internally testing a gemini-4-argon-cyber-permissive variant plus routing models like gemini-3.8-flash-router, alongside a new internal Barium model family.

Wiz's PHP RCE blog credits Gemini 4 Argon for vulnerability discovery, exploit development, attack detection and patch validation, with Google providing mitigation guidance.