Expired50% confidenceBenchmarkExact time
In the same test task, the DeepSeek V4 Pro preview version took approximately 5 minutes and 30 seconds but failed to fix the bug.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/5/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/19/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedDeepSeek V4 Pro scored 37.7 on the Humanity's Last Exam benchmark.69% similarUnverifiedAt the time of its release, DeepSeek-V3 matched or surpassed Claude 3.5 Sonnet on multiple benchmarks, with training costs reportedly a fraction of those of mainstream closed-source models.61% similarUnverifiedUsing V4 Pro with Thinking reasoning mode in the Claude Code environment for a T5 test took approximately 6 minutes and 48 seconds, and the generated page had a layout bug where footer elements appeared in the upper-left corner.60% similarUnverifiedAccording to Commander Code's official internal benchmark data, DeepSeek V4 Pro outperformed Claude Opus in 6 out of 10 high-difficulty tool-dependent tasks.60% similarUnverifiedIn three benchmarks—Agent's Last Exam, ZeroBench, and DeepSWE—V4-Flash-Vision-Exp outperformed Opus 4.8.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/858917API
curl https://kongchang.com/api/v1/knowledge/claims/858917MCP
get_claim(id=858917)