deepseek-v4.1IMAGE
五个 agent 构成通过率-成本帕累托前沿,V4.1 Flash 在列
图表显示 DeepSeek V4.1 Flash、GPT-6.1 Sol、Gemini 4 Argon、GPT-6 Astra、Opus 5.5 构成通过率对成本的帕累托前沿,其余 agent 花更多钱通过更少。
Qiuyang Mang
@MangQiuyang9 天前收录原推发布于 2026.10.23

Qiuyang Mang @MangQiuyang原推发布于 2026.10.23
3/10 Five agents form the Pareto frontier of pass rate against cost: DeepSeek V4.1 Flash, GPT-6.1 Sol, Gemini 4 Argon, GPT-6 Astra and Claude Opus 5.5. Every other agent pays more for fewer passes than one of these five.
x.com/mangqiuyang/status/2113299586068754858采集于 2026.10.23 12:07