Unverified50% confidenceBenchmarkExact time
Qwen3.5-122B-A10B produced 8 refusals in 100 tests, with a KL divergence of 0.0856.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/7/2026
First Seen
Valid until: 12/6/2026
Sources
Related Entities
Related Claims
UnverifiedQwen2.5-72B approaches the performance of Llama-3.1-405B across multiple benchmarks.76% similarUnverifiedQwen2.5-7B-Instruct's performance on multiple Chinese benchmark tests is close to or even surpasses that of early 70B-level models.68% similarUnverifiedAlibaba Cloud's Qwen team released the Qwen2.5-Max-0902 checkpoint.67% similarUnverifiedQwen3 27B在OpenAI HumanEval 164道Python题上取得85%通过率和99%应答率64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/869600API
curl https://kongchang.com/api/v1/knowledge/claims/869600MCP
get_claim(id=869600)