Unverified50% confidenceBenchmarkExact time
在博主自建的GoldieBench评测中，Agent A1 得分4.8/10，排名第二，超过Gemma 4但与Qwen系列（约7.14分）有明显差距
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/22/2026
First Seen
Valid until: 10/20/2026
Sources
Related Claims
Unverified在本地推理速度对比中，Agent A1（95 tokens/秒）快于Gemma 4 Coder和Qwen系列61% similarUnverifiedOmniMerge V4在HumanEval测试中得分84.76，与Q6K原版持平58% similarUnverified千问3.6 Plus综合得分69.0分，排名末位被淘汰出局57% 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 Flash57% similarUnverified跑分排名不等于所有场景的实际表现，Terra跑分接近5.5但游戏任务中5.5完成度略高56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/593885API
curl https://kongchang.com/api/v1/knowledge/claims/593885MCP
get_claim(id=593885)