Gemini 4 Carbon 基准测试显示优于 Opus 5.5
原标题：According to Artificial Analysis, Gemini 4 Carbon is both smarter and cheaper than Opus 5.5 per task...
45AI 研判分
Artificial Analysis 数据显示，Google 的 Gemini 4 Carbon 在任务智能性与成本效益上均超越 Anthropic 的 Opus 5.5。然而，该结论基于 Antigravity CLI 环境下的测试，引发关于不同推理框架下性能一致性的质疑。开发者计划通过 Codex 和 Omnigent 等工具进行独立复现验证。
报道正文
Yuchen Jin (@Yuchenj_UW) · 2026-10-28 17
According to Artificial Analysis, Gemini 4 Carbon is both smarter and cheaper than Opus 5.5 per task.
My only caveat: they benchmarked Gemini 4 Carbon using Antigravity CLI.
I haven't touched Antigravity in months, and I'm not eager to install it...
Will try it out in Codex and Omnigent to see how good it really is.
