Unverified50% confidenceBenchmarkExact time
在本地推理速度对比中，Agent A1（95 tokens/秒）快于Gemma 4 Coder和Qwen系列
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/22/2026
First Seen
Valid until: 10/20/2026
Sources
Related Claims
Unverified在BugFind代码找Bug测试中，Qwen3.6 27B Q4精度得了87分，比Q6的80分更高，出现了量化反转现象67% similarUnverified在HLE科学类基准上，Agent A1 据实测数据超过了Qwen 3.6和Step 3.5 Flash67% similarUnverifiedQwen 3.6 35B A3B在长上下文记忆基准测试中相比Gemma 4和Qwen 3.5具有明显优势66% similarUnverified在三台手机离线测试中，iQOO 15运行Gemma 4 1/2B模型的速度最快64% similarUnverified使用Qwen3 27B Q4量化稠密模型实测，关闭思考模式下生成速度约58-60 Token/s64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/593892API
curl https://kongchang.com/api/v1/knowledge/claims/593892MCP
get_claim(id=593892)