Expired50% confidenceBenchmarkExact time
After enabling thinking and low reasoning, Qwen was able to run formulas such as =A1+B1 and =AVERAGE(A1:B1) in the spreadsheet task and return usable results, while DeepSeek still could not select cells.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
8/30/2026
First Seen
Valid until: 9/13/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedOpen-source models such as DeepSeek-R1 and Qwen-QwQ are actively exploring slow-thinking inference directions similar to o1.74% similarUnverified在同等参数规模下 DeepSeek Math 的数学推理能力强于 Llama、Qwen 和 WizardMath 等开源模型70% similarUnverifiedOpen-source models such as DeepSeek-R1 and Qwen's QwQ are actively exploring a reasoning-enhancement approach similar to o170% similarUnverifiedOpen-source models such as DeepSeek-R1 and Qwen-QwQ have made significant progress in the direction of reasoning enhancement (chain-of-thought reasoning).67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/823802API
curl https://kongchang.com/api/v1/knowledge/claims/823802MCP
get_claim(id=823802)