gemini-4IMAGE
Gemini 4 Argon 登顶 deepswe 与 automationbench 但仅限受邀测试
称 Gemini 4 Argon 在 deepswe 和 automationbench 拿到 77.9% 与 51.3% 第一,却仍锁在 Google 的 trusted testers 里,没人因此离开 Claude Code 或 Codex。
Wes Winder
@weswinder20 天前收录原推发布于 2026.10.10

Wes Winder @weswinder原推发布于 2026.10.10
gemini 4 argon is #1 on deepswe and automationbench 77.9% and 51.3% but it's still locked behind google's "trusted testers" meanwhile, nobody i know is leaving claude code or codex for antigravity benchmarks literally don't matter. just ship it.
x.com/weswinder/status/2108684231249641580采集于 2026.10.12 10:03