Partially Verified75% confidenceBenchmarkExact time
DeepSeek V4.1-Flash-1017 improves by 11 points on the Terminal-Bench 4.0 benchmark compared with the previous version.
3
Sources
75%
Confidence
Short-term (~14 days)
Relevance
10/17/2026
First Seen
Valid until: 10/31/2026
Sources
Related Entities
Related Claims
UnverifiedAmong the 11 benchmarks published by DeepSeek, 1017 surpasses the previous generation on all of them: Tools rose from 36.8 to 42.6, DeepSWE from 74.2 to 77.0, ProgramBench from 20.3 to 29.1, and TerminalBench 4.0 from 31.2 to 42.3.75% similarUnverifiedDeepSeek V4.1 Flash 1017's score on the HLE benchmark rose from 36.8% to 42.6%.73% similarUnverifiedDeepSeek-V4.1 achieves a 22% improvement in time-to-first-token speed on long prompts.71% 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70% similarPartially VerifiedDeepSeek-V4.1-Flash-1017 scores 77.0 on DeepSWE v1.1, surpassing Claude Opus 5's 74.0.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1052780API
curl https://kongchang.com/api/v1/knowledge/claims/1052780MCP
get_claim(id=1052780)