Unverified50% confidenceBenchmarkExact time
Qwen3-4B在多项推理类评测指标上已与DeepSeek V3或GPT-4o相差无几
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/21/2026
First Seen
Valid until: 10/19/2026
Sources
Related Claims
UnverifiedQwen3.5的参数激活率为4.3%，而DeepSeek V3的671B模型激活率为5.5%79% similarUnverifiedQwen3.5在HLE博士级综合题评测中得分28.7，而GPT-5.2为35.577% similarUnverifiedQwen 3's flagship version matches or surpasses GPT-4o and Claude 3.5 Sonnet in multiple benchmark tests.77% similarUnverifiedQwen3.5在IFBench指令遵循评测中得分76.5，超过GPT-5.2的75.4和Claude 4.5 Opus的5877% 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75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/583666API
curl https://kongchang.com/api/v1/knowledge/claims/583666MCP
get_claim(id=583666)