Partially Verified65% confidenceBenchmarkExact time
DeepSeek-V4.1-Flash-1017 achieves 77.0% accuracy on the DeepSWE coding benchmark at an average cost of slightly under $0.20 per task (highest setting), with about 72% accuracy at about $0.10 in the low setting.
3
Sources
65%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
Related Entities
Related Claims
VerifiedDeepSeek replicated top-tier model performance at extremely low compute costs.77% similarUnverifiedThe API pricing for DeepSeek Flash is typically only 1/10 to 1/20 that of top-tier models.74% similarUnverifiedDeepSeek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74% 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% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1058851API
curl https://kongchang.com/api/v1/knowledge/claims/1058851MCP
get_claim(id=1058851)