Expired85% confidenceFactTime unknown
DeepSeek V4 Pro automatically generated 11 UI automation test cases within 12 minutes and 11 seconds, passing two consecutive runs stably.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedDeepSeek V4采用MUON优化器替代AdamW进行训练71% similarUnverifiedThe DeepSWE benchmark was introduced by datacurve.ai and is described as a 'long-cycle software engineering benchmark'.71% similarUnverifiedDeepSeek V4 performed steadily in the full-stack coding test with largely complete functionality, but had shortcomings in some animations, ranking second.71% similarUnverifiedSubsequent versions of DeepSeek V4 will support native multimodality, but multimodality is only one component; the main focus remains on improving AI training and solving continual learning.70% similarUnverifiedDeepSeek, as a free model, performed impressively in AI programming tool tests, exceeding expectations.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/20273API
curl https://kongchang.com/api/v1/knowledge/claims/20273MCP
get_claim(id=20273)