Artificial Analysis benchmarks 26 Search APIs across 14 providers in new agent-search leaderboard
ArtificialAnlys · x · 2026-11-11
Artificial Analysis launched a Search API benchmark and leaderboard covering 26 products from 14 providers, measuring how well search APIs ground AI agents with up-to-date web sources (data as of Nov 9, 2026).
- Score is the equal-weighted mean of DeepSearchQA (F1), BrowseComp (exact-answer accuracy), and AA-Omniscience accuracy.
- On speed, Keenable takes 15.0s (realtime) and 15.5s (pro) per task — 2nd and 3rd fastest behind Octen (14.6s), against a board median of 28s; search itself accounts for only 2.3-3.0s of that, the rest is model time.
- Both Keenable modes sit on the quality-vs-time frontier: no product scores higher in less time.
- The team also open-sourced Stirrup, the agent harness used for all Search API results, with methodology and settings published.
Related event: Artificial Analysis Ranks Search APIs; Keenable Search Takes Top Spot(4 posts)→
More from coding & agent
- LlamaIndex to demo parsing hundreds of pages of insurance medical records with LlamaParse — llama_index · 2026-11-11
- LlamaParse Live Demo: Parsing Hundreds of Pages of Faxed Insurance Medical Records — llama_index · 2026-11-11
- Nous Hermes agent turns an idea into printable CAD, iterating on slide-fit lid mechanism — Teknium · 2026-11-11
- EMNLP survey organizes LLM routing into predictive, adaptive and generative paradigms — kalyan_kpl · 2026-11-11
- Telegram Now Turns Any Message Into an App Under 4KB With Built-in Payments — CurieuxExplorer · 2026-11-11
- thimble: open-source Claude Code plugin makes agent outputs explainable in your terminal — AlexTamkin · 2026-11-11