Expired50% confidenceFactExact time
MAI Thinking-E performs strongly in reasoning-intensive domains such as mathematics and science, but in coding tests it only reached the level of DeepSeek V3.2.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
Related Claims
UnverifiedBenchmark tests show that Qwen3-235B's performance matches or even surpasses DeepSeek R1, with advantages in categories such as math, coding, and reasoning.70% similarUnverifiedPhi-3-mini（3.8B参数）在部分基准测试上超越了Mixtral 8x7B等更大的混合专家模型63% similarUnverifiedMAI Thinking-E has a total parameter count of approximately 1T (trillion), with approximately 35B activated parameters, and uses a MoE (Mixture of Experts) architecture.62% similarUnverifiedQwen3.7 Max maintains a leading position on high-cognitive-intensity tasks such as mathematical reasoning and logical analysis61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/46131API
curl https://kongchang.com/api/v1/knowledge/claims/46131MCP
get_claim(id=46131)