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

A same-month year-over-year comparison of flagship models argues Gemini 4 Argon ranks second in long-horizon engineering with the industry's lowest 15% hallucination rate, while GPT-6 Astra is narrowly specialized and Opus 5.5 still leads on complex tasks.

A user ran the gemini-4-argon checkpoint in Arena on a voxel steampunk brass kraken prompt and called it their best output so far.

The author says Gemini 4 Argon on LMArena produced a clean interactive digital sketchbook, arguing the entry actually routes to a Gemini 4 Carbon checkpoint.

A user shares two Arena session links so others can compare outputs from gemini-4-argon-high and the gemini-4-argon Carbon checkpoint.

NovaXCode says Gemini 4 Argon once burned a weekly limit in an hour, and the stronger Gemini 4 Carbon might wipe it out in 10 minutes.

A user reports two distinct behaviors under the Arena name gemini-4-argon: one fast and solid, another very slow but impressive, possibly the Carbon checkpoint.

A post citing Sundar Pichai says Gemini 4 Argon consumed nearly 25 trillion tokens in 72 hours, triple Gemini 3.0, leaving Google short on compute and slowing its rollout.

A user complains that Gemini 4 Argon is available to Pro subscribers in Antigravity but not in Google AI Studio, questioning why access is limited to one platform.

A user posts a video showing test output from the Gemini 4 Carbon checkpoint labeled gemini-4-argon in Arena.

A user says an Arena code battle produced an output labeled gemini-4-argon, which they found better than Argon.

Four models each generated a one-shot POV night walk through Matera; Gemini 4 Argon took 46 minutes and $4.50, versus Opus 5.5 at 4h 11m and $76.

Leaks say Carbon is in partner EAP and LMArena testing, beating Argon at 3D but still weak on frontend, with coding possibly matching Opus 5.5.