Unverified50% confidenceBenchmarkExact time
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83.9
1
Sources
50%
Confidence
Long-term
Relevance
7/10/2026
First Seen
Sources
华为盘古2.0-Flash横评：指令遵循第一，代码工程垫底
bilibiliAI观模者6/30/2026
Related Claims
Unverified在AIME-2024基准上，DeepSeek-V4 Flash的pass@1从0.39提升至0.4971% similarUnverifiedDeepSeek V4 Flash综合得分84.7分排名第三，完成速度最快仅7分30秒68% similarUnverifiedDeepSeek V4 Flash在OpenModel平台的速率限制为每分钟10次请求（10 RPM）和每分钟100K tokens（100K TPM）66% similarVerifiedDeepSeek V4 Flash拥有284B总参数，每次激活13B，显存需求约150G65% similarUnverified盘古2.0 Flash恰好填补了当前开源社区在27B到200B之间的空缺，此前没有一款90B左右的开源MoE模型65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/463523API
curl https://kongchang.com/api/v1/knowledge/claims/463523MCP
get_claim(id=463523)