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

The poster notes that GPT-6 Pro was evaluated in the ChatGPT harness and Gemini 4 Pro in the arena.ai harness, yet the two different models produced basically identical results, and questions the evaluation method.

The poster says Gemini 4 Pro's SVG output beats GPT-6 Astra and Claude Fable, while citing a LuminaBench post that the model's release has been delayed.

In an interview, Google DeepMind's Koray Kavukcuoglu says being at the frontier is the team's only goal and that he is 100% certain it will get there, with a link to a roundup of Gemini 4 progress.

The author posts a video captioned only "Gemini 4 Pro," without describing what was tested or any conclusion.

The author says Gemini 4 Pro is very strong in areas like design and 3D modeling but rough in others, because Google specializes models for fields like math rather than building all-round general models.

LuminaBench replies that Gemini 4 Pro can generate exploded views showing internal components with part names.

An unidentified Google model has surfaced in Arena testing, rumored to have 10M-token context, a big coding jump and persistent memory, possibly a Gemini 4 checkpoint.

A model reportedly routed through a gemini-3.7-flash Arena label generated a full interactive SVG product page with color variants, draggable controls and SVG download; Google has not confirmed its identity.

A poster argues that Gemini 4 Pro and Astra produce nearly identical results because the benchmark used is saturated at the top and can no longer separate models.

A user reading LuminaBench results says Gemini 4 and GPT-6 Astra are extremely close, but notes that Gemini drew the logo correctly.

On the same SVG prompt, Gemini 4 Pro and GPT-6 Astra both come out near perfect, though Astra's logo is slightly off, and the gap to other models is large.

A joking post says Gemini is no longer chosen by vibe coders and that only the release of Gemini 4 Pro can save Google CEO Sundar Pichai.