Expired50% confidenceBenchmarkExact time
On the Artificial Analysis leaderboard, the Step 5 preview achieves an intelligence score of 44, surpassing Kimi K3 and GLM at approximately 2.8 trillion parameters, ranking just below Astra and Opus 5.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/24/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/8/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedGLM 5.2 scored 51 points on the Artificial Analysis Intelligence Index in its MAX version, making it the highest-scoring open-weight model currently available.72% similarUnverifiedArtificial Analysis gave Qwen 3.8 an intelligence index of 52, tying GPT at the full reasoning tier at 5.6, with an agent score of 51, higher than Claude Opus 4.8.71% similarUnverifiedThe upgraded Tongyi Qianwen model released by Alibaba has a parameter scale of 2.4 trillion, slightly smaller than Kimi K3.69% similarUnverifiedGLM-5.3在六项评测中的成绩为：终端编程基准3.0得28.3、深度软件工程基准得66.9、智能体中场考试得28.5、自动化基准得48.2、带工具的人类终极考试得62.5、GDP价值评估AA2版得17.6967% similarPartially VerifiedMiMo V2.6 Pro scored 46 points on the Artificial Analysis overall intelligence leaderboard, tying with Grok 4.7 for sixth and seventh place.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/947143API
curl https://kongchang.com/api/v1/knowledge/claims/947143MCP
get_claim(id=947143)