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

Gemini 4 Argon (high) scored 20.2% on WeirdML, landing between Sonnet 5.5 and Fable 5.1, strong but still behind the frontier on token efficiency.

A developer advises against using Gemini 4 Argon to write complex systems directly, praising it for building tools and reviewing Opus's tech choices, suggesting a 300k auto-compaction cap and noting it clashes with GPT.

A short poll asks readers to pick the best coding model right now among GPT-6 Astra, Opus 5.5 and Gemini 4 Argon, and explain why.

A Japanese developer tested how far Claude Code can build a video using only code, and had Gemini 4 Argon write the prompt itself; the result video is attached.

In a same-prompt test where six models designed 3D-printed capsules to protect a raw egg, Gemini 4 Argon placed third with a slight crack at 4 ft; only Opus 5.5 and GPT-6 Astra cleared 4 ft.

A user reports Gemini 4 Argon made limited progress and many mistakes building on a compiler, needing Fable to clean up, while Meta Muse Wonder Full made none in a similar test.

A short post says Gemini 4 Argon's main remaining problem is its quota, which can't support intensive work.

A user claims Gemini 4 Argon decisively outperforms GPT-6 Astra Pro at rewriting dry papers into accessible popular-science articles.

The poster says Gemini 3.8 Flash now gives completely different, heavily hallucinated answers on the same prompts and workflow since Gemini 4 Argon arrived, suspecting a quiet nerf.

An app that sends product photos to Gemini 4 and flags what's wrong with the food is cited as making $300k a month, pitched as the 2027 app idea.

The poster finds Gemini 4 Argon possibly underwhelming overall but says its code stays maintainable without the model, unlike output from GPT 6.1 Sol.

On one identical prompt, Gemini 4 Argon cost $7.84 and took 23 minutes, far less than Sonnet 5.5, Opus 5.5 and GPT-6 Astra; the author asks which did best.