Web Search Changes LLM API Recommendations, Usage Varies by Model
Supplementary data shows large gaps in how often models use an optional web search tool—Opus 5.5 searched in only 10 of 60 responses while GPT models searched nearly every time—and enabling search cut big-cloud API recommendations from 79% to 60%.
2026-11-17 ~ 2026-11-17 · 2 related posts
- Web search shifts LLM API picks: big clouds fall from 79% to 60% of recommendations — santiviquez · 2026-11-17
- Search behavior gap: Opus searched in 10/60 answers, GPT models searched every time — santiviquez · 2026-11-17