Unverified50% confidenceBenchmarkExact time
DeepSeek V4.1 Flash在Deep SWE软件工程代码测试上拿到74分，是UP主见过的第一个在Deep SWE上达到74分的开放权重模型
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/16/2026
First Seen
Valid until: 12/15/2026
Sources
Related Entities
Related Claims
UnverifiedDeepSeek的编程智能体DeepSWE在SWE-bench基准测试中从预览版的12.8分提升至62.7分77% similarPartially VerifiedDeepSeek V4.1 Flash 在 GPQA、HLE 等方面的评分低于此前版本77% similarUnverifiedDeepSeek V4.1 Flash在AA新的私有评测基准上超越Astra登上榜首75% similarUnverifiedDeepSeek V4.1 Flash在测试时处于内测阶段，但通过直接调用模型ID已可正常访问75% similarUnverifiedDeepSeek V4.1 Flash 采用 Causal Encoder-Decoder 非对称架构，总参数量为 552B74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/924489API
curl https://kongchang.com/api/v1/knowledge/claims/924489MCP
get_claim(id=924489)