GDPx 基准测试：Claude Opus 5.5 智能体得分 12%，Gemini 4 性价比更高
精选理由
GDPx 这个基准挺有意思，用 206 个真实经济任务测智能体。Opus 5.5 分最高，但 Gemini 4 便宜 4 倍只低 1.1%，选型可以参考。
GDPx 基准测试用 206 项任务评估 AI 智能体在芯片设计、软件工程、金融、生物等 11 个经济价值领域的能力。Claude Opus 5.5 以 12% 的得分排名第一，Gemini 4 Carbon 以 10.9% 紧随其后。两者得分只差 1.1%，但 Gemini 4 的价格约为 Opus 5.5 的四分之一，性价比上明显占优。
原文 · kimmonismus
Super interesting Benchmark. GDPx measures how well AI agents handle 206 challenging tasks across 11 economically valuable fields, including chip design, software engineering, finance, and biology.
But here's the interesting part: Opus 5.5 wins with 12%, closely followed by Gemini 4 Carbon with 10.9%. But while performing just 1.1% worse, Gemini 4 is about 4x cheaper than Opus 5.5. So cost-performance wise Gemini 4 wins by a lot.
- rohanpaul_ai12:45原文
