Unverified50% confidenceBenchmarkExact time
Muse-Glimmer在九大维度中赢了五个，其中数据提取领先约4.55分为最大差距项，工具/CLI领先3.5分
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/16/2026
First Seen
Valid until: 11/14/2026
Sources
Muse-Glimmer-30B实测：24G显存跑出九维跑分76分的性价比之王
Related Claims
UnverifiedMuse Glimmer scores 75.5 on the MCP Atlas tool-calling benchmark, leading Qwen 3.6; scores 74.6 on agentic search tasks; and scores 94.7 on the AIME mathematical reasoning benchmark.76% similarUnverifiedMuse Glimmer scored a total of 36 points in real-world testing, ranking second to last among 6 models, 4 points lower than Qwen 3.6 27B.74% similarUnverifiedMuse Glimmer在DeepSearch QA得分74.6，SWE-Bench Pro得分51.273% 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 27B71% similarUnverifiedMuse-Glimmer-30B achieves a comprehensive lead over Grok-4's 31B model.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/757566API
curl https://kongchang.com/api/v1/knowledge/claims/757566MCP
get_claim(id=757566)