Unverified50% confidenceFactExact time
DeepSeek V4 Pro的参数规模远小于Kimi K3或Qwen3.8这类模型
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/23/2026
First Seen
Valid until: 11/21/2026
Sources
Related Entities
Related Claims
UnverifiedDeepSeek V4 comprehensively leads Qwen 3.5, Kimi K2.6, Gemma 5.1, and other open-source models across all metrics.77% similarUnverifiedDeepSeek V4 chose not to use N-gram technology, abandoning the Multi-token Prediction combined with N-gram approach that had been explored in V3/R1.72% similarVerifiedDeepSeek-V3 outperformed open-source models such as Qwen2.5 and Llama 3.1 in multiple benchmarks.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/791277API
curl https://kongchang.com/api/v1/knowledge/claims/791277MCP
get_claim(id=791277)