Expired50% confidenceBenchmarkExact time
QDAM 3.7 Plus's weaknesses include a tendency toward excessive thematic elevation, thin period-specific details, and insufficient web novel feel.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/9/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/7/2026(expired)
Sources
Domestic Budget AI Models for Web Novel Writing: A Head-to-Head Comparison of Four Models
bilibili灵蟹SoloEnt7/5/2026
Related Claims
UnverifiedQwen 3.8 Max may not perform stably enough during long-running tasks, with occasional issues such as failing to create files when it should during longer sessions.72% similarUnverifiedQwenCoder fell into an infinite loop on the complex task, exhibiting a 'context window degradation' phenomenon—logical inconsistencies between earlier and later content when the generated output exceeded the effective processing length.65% similarUnverifiedQwen3 27B by default initiates the full long-chain reasoning process even for simple questions, meaning it exhibits an overthinking problem.64% similarUnverifiedCascaded architectures suffer from latency accumulation, as the sequential execution of three modules increases response time and results in a less fluid conversational experience.64% similarUnverifiedQ3量化版本的MTP层效果反而比Q4更慢，因为更低精度导致更多预测被主模型拒绝，触发更频繁的回滚操作63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/329239API
curl https://kongchang.com/api/v1/knowledge/claims/329239MCP
get_claim(id=329239)