gemini-4IMAGE
Gemini 4 Argon 编程 benchmark 实测：中等水平
作者跑自家 LLM 编程基准，结论是 Argon 比 Gemini 3.x Flash/Pro 强很多，但仍落后前沿模型，且慢、API 贵、Pro 版 Antigravity 用不了。
Povilas Korop | AI Coding & Laravel Educator
@PovilasKorop21 天前收录原推发布于 2026.10.15
Povilas Korop | AI Coding & Laravel Educator @PovilasKorop原推发布于 2026.10.15
So I ran my LLM coding benchmarks on Gemini 4 Argon. The result is... average. It's MUCH better than Gemini 3.x Flash/Pro. But still WAY behind the frontier models. Also too slow. And expensive on API pricing. And not available on Antigravity on Pro plan. Sooo over-hyped.
x.com/povilaskorop/status/2110406549755593002采集于 2026.10.15 11:36