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

A user says Gemini 4 Pro performs impressively at 3D generation and calls it very tempting, without sharing any specific output.

The author shares a video generated with Gemini 3.1 Pro and says that if the leaked Gemini 4 Pro benchmarks are real, its output is hard to imagine.

The author shares a Three.js scene made with GPT Astra Ultra, saying Astra remains the best pick for Three.js and questioning how strong Gemini 4 Pro really is.

The author ran the Will Smith eating spaghetti test in Three.js, was impressed by the result, and speculated that Gemini 4 Pro's frontend generation is nearing Fable 5.

YouWare built a 3D version of the classic AI stress test, pitting Gemini 4 Pro against Fable 5 Max side by side and calling the results beyond expectations.

A poster lists four models that could ship next week, placing Gemini 4 Pro alongside Opus 5.5, Grok 4.7 and GPT-6 Sol.

An AI daily digest says Sonnet 5.2, Opus 5.2, Fable 5.2 and Gemini 4 Pro are all in testing, alongside news that GPT-6 Astra solved a long-open math problem.

A complaint post questioning the gap between Gemini 4 Pro's claimed capability and its actual product experience.

A user says Gemini 4 Pro's early Three.js results look strong and asks whether it can beat GPT-6 Astra and Fable 5.1.

A model labeled Gemini 3.7 Flash on Arena generated a three.js mechanical butterfly from a prompt, prompting guesses it is the unreleased Gemini 4 Pro, which Google has not confirmed.

A joking image-only post asserting that Gemini 4 Pro will crush Opus 5.5, with no benchmark data.

A short post with a video reacting to Gemini 4 Pro's output, without specifying the task or what it was compared against.