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

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.

The author says the anonymous gemini-3.8-flash model on Arena is likely a disguised Gemini 4 Pro test that Google hasn't confirmed, and suggests buying Google Pro membership early.

A short post saying the author is most excited and curious about Gemini 4 Pro and asking whether Google can return to the frontier.

The blogger asks which model will launch first among GPT-6 Sol, Gemini 4 Pro and Grok 4.7, betting on the long-delayed Grok 4.7.