Search behavior gap: Opus searched in 10/60 answers, GPT models searched every time
santiviquez · x · 2026-11-17
Supplementary data from the API recommendation experiment: with an optional web search tool, usage diverged sharply — Opus 5.5 searched in only 10 of 60 answers (0.8 queries each), Fable 5.1 in 24, while both GPT models searched all 60 times (2.3 and 3.2 queries each).
The author also previously found that enabling web search dropped big-cloud API recommendations from 79% to 60%, while smaller parsing startups rose from 5% to 13%.
Related event: Web Search Changes LLM API Recommendations, Usage Varies by Model(2 posts)→
More from Models
- 'Humans Also Read Linearly and Causally, So It's Not a Transformer Issue' — yacineMTB · 2026-11-17
- Fudan & OpenMOSS map the trade-off: long-context hybrids learn more, extrapolate less reliably — jiqizhixin · 2026-11-17
- Models favor their own APIs in code: Opus calls Claude API in 97% of implementations — santiviquez · 2026-11-17
- 79% of 2,880 LLM API recommendations went to just four big-cloud services — santiviquez · 2026-11-17
- Hy4 Flash hands-on: DeepSeek-V4.1-level quality at ~1/15 the cost, 60% faster — IlovedamemesUwU · 2026-11-17
- Memory eval leaderboards are misleading: OmniMemEval mixes conditions and tunes on its own benchmark — Snoo-bedooo · 2026-11-17