Kimi K2.7 ranks second behind Fable 5 and above GPT 5.5 xhigh in ErdosBench's mathematical research test

Przemek Chojecki's 14-problem smoke run puts Moonshot's new open-weight model behind Claude Fable-5-max and ahead of GPT-5.5 xhigh.

By · Published

Primary source: X

Why it matters

Kimi K2.7 Code's ErdosBench result suggests open-weight models are pushing beyond cheap coding help into proof-aware research workflows, where hygiene matters as much as raw answers.

Illustration of the Kimi K2.7 model ascending a tiered ErdosBench chart, placed below Claude Fable-5-max and above GPT-5.5 xhigh.

Przemek Chojecki (@prz_chojecki) put Kimi K2.7 Code in the top tier of his ErdosBench public smoke test on June 13th, ranking Moonshot AI's new coding model second behind Claude Fable-5-max and ahead of GPT-5.5 xhigh.

…

When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

Reader comments

Conversation for this story loads after sign-in.