RTK reports huge token savings, but our cost benchmarks disagree

Quesma，面向前沿实验室与企业的 AI 独立评估与培训。关注
RTK reports huge token savings, but our cost benchmarks disagree 图片 1

We tested RTK (Rust Token Killer) with Claude Code on Fable 5.0, and OpenCode with DeepSeek V4 Pro 0813 on Terminal-Bench 2.1.

添加评论
点赞收藏
点踩分享查看原文
评论
?
参与讨论