Unverified50% confidenceBenchmarkExact time
据Artificial Analysis数据，Qwen 3.8的270亿参数模型在Agentic指数上拿到51分，超过GPT-5.6 Terra、DeepSeek v4 Pro、GPT-5.6 Luna以及Gemini 3.7 Flash
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
8/22/2026
First Seen
Valid until: 9/5/2026
Sources
Related Entities
Related Claims
VerifiedQwen 3.6 是一个270亿参数的稠密模型73% similarUnverifiedQwen3-4B在多项推理类评测指标上已与DeepSeek V3或GPT-4o相差无几73% similarPartially Verified通义千问发布了Qwen 3.8 Max模型，参数规模高达2.4万亿72% similarUnverified综合实测结果，四款模型能力排名为：Sol > GPT-5.5 > Terra > Luna70% similarUnverifiedQwen3.5的参数激活率为4.3%，而DeepSeek V3的671B模型激活率为5.5%70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/787060API
curl https://kongchang.com/api/v1/knowledge/claims/787060MCP
get_claim(id=787060)