Verified80% confidenceFactExact time
Pangu 2.0 Flash adopts a MoE (Mixture of Experts) architecture with a parameter scale of 92B A6B (92B total parameters, 6B activated parameters).
6
Sources
80%
Confidence
Long-term
Relevance
7/9/2026
First Seen
Sources
Huawei Pangu 2.0 Flash on the Gaokao Benchmark: 613 Points, Stability Issues, and Cost Breakdown
bilibiliwycode_cn7/7/2026
Related Claims
Unverified盘古2.0 Flash在GPQA Diamond科学推理测试中（Thinking模式）得分83.7，低于千问3.6 35B的86、27B稠密模型的87.8和DeepSeek V4 Flash的88.175% similarUnverifiedV4.1 Flash scored 74.2 on the SWE software engineering benchmark, 90.6 on the terminal benchmark, and 3,471 points on Tonka Forces evaluation (vs. 3,348 for VS Pro).73% similarPartially VerifiedQwen3.8-Flash-Next adopts a Mixture of Experts (MoE) architecture with 125B total parameters and 6B activated parameters.73% similarVerifiedDeepSeek V4 Flash uses a Mixture of Experts (MOE) architecture with a total parameter count exceeding 600 billion (600B+).71% similarUnverifiedQwen3.8 Flash Next is a Flash model using the next-generation Qwen4 architecture, and the complete weights were released on the day of its open-sourcing.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/330493API
curl https://kongchang.com/api/v1/knowledge/claims/330493MCP
get_claim(id=330493)