Unverified50% confidenceFactExact time
Fable 5在电商网站测试中输出Token为58.8万，而Opus 4.8输出Token为489.8万，Fable 5的Token使用量约为Opus 4.8的12%
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Fable 5 vs Opus 4.8实测对比：三大项目验证谁是AI编程王者
bilibili未来变量relaunch6/12/2026
Related Claims
UnverifiedIn the e-commerce website test, Opus 4.8 consumed 4.898 million output tokens while Fable 5 used only 588K tokens77% similarUnverifiedFable 5在SWE Bench Pro编程测试上得分80.3分，而OpenAI的GPT 5.5仅为58.6分70% similarUnverifiedFable 5在规划阶段生成的计划长度是Opus 4.8版本的两倍以上，但在结构性和可读性上被测试者认为不如Opus 4.8的版本68% similarUnverifiedExploitBench测试中Sol约76%略逊于Fable 5的78%，但Sol仅消耗约12-13万Token而Fable 5用约35万Token63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/48735API
curl https://kongchang.com/api/v1/knowledge/claims/48735MCP
get_claim(id=48735)