Gemini 4 Argon ranks first or second on most benchmarks, roundup says
A roundup says Gemini 4 Argon has the lowest hallucination rate, tops the Vals index and text arena, scores 53 on AA to match Astra, and costs less per task but is not token efficient.

google team cooked harder with this model almost all benchmark scores are live now and gemini 4 argon is ranked first or second on most of them and model: > has lowest hallucination rate > tops vals index > ranked first on text arena > scored 53 on AA, same as astra > cheaper than astra, sonnet, fable and opus per task > not token efficient sadly i don’t trust benchmarks much, but these numbers look are looking good man if someone from google team is reading this, please gib access, wanna test model and post about it is this google comeback?