Unverified50% confidenceBenchmarkExact time
Among 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.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
DeepSeek New Version Hands-On: Same Price, Costs Slashed by 60%
bilibili枫叶边城10/18/2026
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% similarUnverifiedDeepSeek V4.1-Flash-1017 improves by 11 points on the Terminal-Bench 4.0 benchmark compared with the previous version.75% similarVerifiedThe open-source version of DeepSeek-Coder includes multiple parameter scales such as 1.3B, 6.7B, and 33B.68% similarUnverifiedDeepSeek-V4.1 achieves a 22% improvement in time-to-first-token speed on long prompts.67% similarVerifiedDeepSeek simultaneously updated DeepSeek Harness V0.1.5, with dedicated training and optimization targeting Harness's standard PTC minimal three modes.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1059842API
curl https://kongchang.com/api/v1/knowledge/claims/1059842MCP
get_claim(id=1059842)