V2EX-最热主题
咱们这一辈,真可能是最后一代人类程序员了!
qxmqh: Claude Mythos vs Claude Opus 4.6
SWE-bench Verifed:93.9% -- 80.8%
SWE-bench Pro:77.8% -- 53.4%
SWE-bench-Multilingual:87.3% -- 77.8%
SWE-benchMultimodal:59% -- 27.1%
https://www-cdn.anthropic.com/53566bf5440a10affd749724787c8913a2ae0841.pdf
source
(author: qxmqh)
咱们这一辈,真可能是最后一代人类程序员了!
qxmqh: Claude Mythos vs Claude Opus 4.6
SWE-bench Verifed:93.9% -- 80.8%
SWE-bench Pro:77.8% -- 53.4%
SWE-bench-Multilingual:87.3% -- 77.8%
SWE-benchMultimodal:59% -- 27.1%
https://www-cdn.anthropic.com/53566bf5440a10affd749724787c8913a2ae0841.pdf
source
(author: qxmqh)