Expired50% confidenceEventExact time
During the experiment, DeepSeek V4 Flash released its official version while the Pro version remained in preview, and the Qwen3.8 series had not yet been released, so comparisons used Qwen3.6's 27B and 35B MoE.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/11/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/25/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedDeepSeek V4 Flash ranks higher than the 27B model on the agent intelligence index, whereas the previous 0731 version ranked only 48th.71% similarPartially VerifiedThe 4-bit quantized version (Q4K XL) of Qwen3 Next Flash is approximately 111 GB.69% similarUnverifiedQwen 3.8 Flash has a parameter count of 180B, which is half that of GLM 5.3 Flash (320B).67% similarUnverifiedAlibaba's Tongyi Qianwen officially released Qwen3.8-Flash-Next (Qianwen 308 Flash NEX), with total parameters as high as 181.5B.66% similarUnverified盘古2.0 Flash在LiveCodeBench算法推理测试中得分85.1，仅次于DeepSeek V4 Flash的91.6，超过千问3.6 27B的83.966% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/906139API
curl https://kongchang.com/api/v1/knowledge/claims/906139MCP
get_claim(id=906139)