Partially Verified65% confidenceBenchmarkExact time
DeepSeek-V4.1-Flash-1017 scores 77.0 on DeepSWE v1.1, surpassing Claude Opus 5's 74.0.
3
Sources
65%
Confidence
Short-term (~14 days)
Relevance
10/17/2026
First Seen
Valid until: 10/31/2026
Sources
Related Entities
Related Claims
Unverified在 DeepSWE 基准上 Laguna S 2.1 得分 40.4，而 DeepSeek V4 Pro Max 仅约 9 分74% similarUnverifiedThe price of DeepSeek V4.1-Flash-1017 remains the same as the previous version (deepseek-flash).73% similarVerifiedDeepSeek V4.1 Flash scores lower than the previous version on GPQA, HLE, and other benchmarks.72% similarUnverifiedDeepSeek V4.1 Flash scored 74 on the Deep SWE software engineering code test, making it the first open-weight model the UP host has seen to reach 74 on Deep SWE.72% similarUnverifiedDeepSeek V4.1 Flash 1017's score on the HLE benchmark rose from 36.8% to 42.6%.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1054795API
curl https://kongchang.com/api/v1/knowledge/claims/1054795MCP
get_claim(id=1054795)