Unverified50% confidenceOpinionExact time
Perplexity's connector issue is especially pronounced when using the Sonnet 5 model.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/9/2026
First Seen
Valid until: 11/7/2026
Sources
AI模型GitHub连接器可靠性实测：Kimi与Perplexity谁更值得信赖
Related Claims
Unverified重新用现代模型跑同一任务，Sonnet 4.6只需一次额外迭代就解决问题，Opus基本一次成型（one-shot）69% similarUnverifiedClaude Sonnet 4.5 significantly outperforms the previous-generation Sonnet 4 model on software engineering benchmarks, and even surpasses the higher-positioned Opus model.68% similarUnverified测试者认为Opus 5是优秀的编程模型，能力与Sonnet 5差距不大且价格更低67% similarUnverifiedOn computer use and world knowledge tasks, Sonnet 5 has approached the level of Opus 4.8, but still lags notably behind Opus 4.8 in the domain of agentic programming66% similarUnverifiedIn SVG generation tasks, Sonnet 5's results for generating a BMW M4 CS were completely unsatisfactory, clearly trailing behind GLM, and the tester ranked Sonnet 5 below GLM 5.2.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/721197API
curl https://kongchang.com/api/v1/knowledge/claims/721197MCP
get_claim(id=721197)