Unverified50% confidenceBenchmarkExact time
On the four benchmarks ProgramBench, NL2Repo-Bench, Automation-Bench and Agents' Last Exam, V4.1 Flash 1017 scores 29.1, 68.2, 60.5 and 35.4 respectively, all higher than V4 Pro 0813's 15.5, 61.5, 43.2 and 25.7.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedV4.1 Flash 1017's score on Terminal-Bench 4.0 rose from 31.2% to 42.3%, a relative improvement of 35% in five weeks.77% similarUnverifiedDeepSeek V4.1 Flash 1017 rose from 31.2 to 42.3 on Terminal Bench 4.0, from 20.2 to 42.3 on Program Bench, from 31.8 to 35.4 on Agent's Last Exam, from 64.6 to 72.1 on Apex Bench, from 78.9 to 83.0 on Chartography, and from 89.6 to 92.5 on Baby Vision.74% similarUnverifiedOn knowledge reasoning tasks, V4.1 Flash underperforms V4 Pro: doctoral-level science Q&A scores 90.9 vs. 92.4, and "Humanity's Last Exam" scores 36.8 vs. 42.7.73% similarUnverifiedOn the text-only HLE subset, V4.1 Flash 1017 scores 44.0, surpassing V4 Pro 0813's 42.7.73% similarUnverifiedV4.1-Flash scored 74.2 points on a certain programming test dimension, an improvement of nearly 20 points over V4-Flash.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067645API
curl https://kongchang.com/api/v1/knowledge/claims/1067645MCP
get_claim(id=1067645)