Unverified50% confidenceBenchmarkExact time
On the 50 tasks shared between 2025 and 2026, the model's Q value improved from 0.260 to 0.371; on all 100 tasks, the model scored 0.392.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/11/2026
First Seen
Valid until: 11/25/2026
Sources
Related Entities
Related Claims
UnverifiedAlibaba CEO Wu Yongming stated at the Yunqi Conference on September 22, 2026, that the next generation of Qwen models will be expanded to 5 trillion to 10 trillion parameters and are currently in full-scale training.64% similarUnverified2023-2024年间,部分模型在SWE-bench Verified基准上的问题解决率突破50%61% similarUnverifiedPublicly available reasoning models, with appropriate prompting, can solve all 6 problems of the 2025 IMO.60% similarUnverifiedThe systems in the paper used 2024-25 models, whereas this test used a 2026 model (Claude Sonnet 5.5), so part of the performance gap comes from capability improvements in the model itself.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1158628API
curl https://kongchang.com/api/v1/knowledge/claims/1158628MCP
get_claim(id=1158628)