Unverified50% confidenceBenchmarkExact time
MiMo V2.6 Pro在SWE基准上成绩达到71.9，高于GLM的66.9
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/1/2026
First Seen
Valid until: 12/30/2026
Sources
Related Entities
Related Claims
VerifiedMiMo V2.6 Pro在Artificial Analysis综合智能榜上拿下46分，与Grok 4.7并列第六、第七位69% similarUnverified官方称 MiMo Pro 在某综合指数上拿到 46 分，超过 K3 和 QN，但低于 Fable 和 Astra66% similarUnverified在一道三样本数学题上，DeepSeek V4.1 Flash达到74分，与Opus 5.0持平，超过GLM的67分和V4 Pro的62分65% similarUnverifiedHY3在整体性能上仍落后于GLM 5.2（当前开源模型顶级水平）65% similarUnverified单轮测试排名靠前的是GLM-5.3得分96.2%、Kimi 93.9%、GLM-Flash 92.2%，三者原始分都是79/8464% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/964441API
curl https://kongchang.com/api/v1/knowledge/claims/964441MCP
get_claim(id=964441)