Unverified50% confidenceBenchmarkExact time
Artificial Analysis给Muse Glimmer 30B打出35分的智能指数，相比Llama 4 Maverick是巨大飞跃
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/19/2026
First Seen
Valid until: 11/17/2026
Sources
Related Claims
Unverified根据Artificial Analysis的独立评测，Glimmer 30B的智能指数得分为35分76% similarUnverified在通用智能体任务上Glimmer得分达24%，高于Qwen的17%65% similarUnverifiedDGM在SWE-bench软件工程基准测试中自动将基线性能提升了一倍以上，实现了30个百分点的绝对提升64% similarUnverifiedGlimmer智能指数35分，超越Gemma 2 27B（30分），几乎追平Qwen 2.5（36分），Qwen 2.5 72B以38分居榜首63% similarUnverifiedMuse-Glimmer-30B在智能体工作流得90.87分、指令遵循90.86分、工具/CLI 88.84分，三项均优于Corpus 3.6 27B63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/772781API
curl https://kongchang.com/api/v1/knowledge/claims/772781MCP
get_claim(id=772781)