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

Wiz Research disclosed PHP2Shell, a CVSS 9.2 flaw in core PHP affecting much of the web, saying Gemini 4 Argon helped find the bug, build the exploit chain, create detectors and validate the patch.

The poster hopes Fable 5.5 won't be overhyped like Gemini 4 Argon and asks why Argon still hasn't shipped.

Sundar Pichai says internal evaluations and research breakthroughs indicate Gemini 5 will be much better than Argon, citing durable demand and long-term contracts.

The author tested Gemini 4 Carbon on Arena: it took 2–3x longer than Argon but clearly beat it on visual output quality, with video and prompt included.

A Persian post says Google AI Pro now offers a $4.99/month four-year plan bundling Gemini 4 Argon access with 5TB of cloud storage, arguing the storage alone justifies the price.

Google DeepMind used Gemini Argon to reduce Turing machine state counts for Goldbach's Conjecture, the Riemann Hypothesis and ZF consistency, verifying each reduction end-to-end in Lean 4 and open-sourcing the code.

The poster expects Google DeepMind's Gemini 4 Carbon soon and debates whether it ships as Gemini 4.1 Carbon or a new class in the 4.0 family.

Citing Toby's finding, Gemini 4 (Google Argon) sustains real-world AI research tasks for about 15 minutes, far below the 6-hour METR and 18-hour AI 2027 forecasts.

A user asks Gemini 4 Carbon to build a 3D bicycle riding a cow in three.js, praising the 3D output and comparing it to Astra and Opus 5.5.

The author had Gemini 4 Argon build a periodic table synced to Tom Lehrer's 'The Elements', then gave the same prompt to Opus 5.5 and posted a video comparing the two results.

A developer implemented the robotics harness described in Gemini 4 Argon's report; Gemini completed a zero-shot bimanual handover, and the code is now open source with a demo video.

The poster argues OpenAI is only shipping point updates like gpt-6.1 sol, while Google has shipped Argon and is reportedly already working on Carbon.