Keenable Search 1.0 tops Artificial Analysis Search Index at 83, a third below median cost
ArtificialAnlys · x · 2026-11-11
Artificial Analysis benchmarked Keenable Search 1.0 across 1700 search tasks using GPT-5.6 Luna (medium) in its Stirrup agent harness.
Key results:
- Keenable pro scores 83 and realtime 82 on the Search Index, ahead of Exa (auto, dynamic highlights) and Perplexity (medium) at 80 — up from 67 in August and 50 points over the same model without search (33)
- Both modes hit 88 F1 on DeepSearchQA, 1st and 2nd of 26; pro also leads BrowseComp (87%) and ties on AA-Omniscience (73%)
- At $4 per 1k searches, total cost is $0.040 per task, over a third below the board median ($0.063); search accounts for 80% of it
- Fastest tier of the board: 15.0s/15.5s per task, with individual searches returning in 330-390ms vs a 12.5s median
Search cards were disabled during testing.
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
- Cloudflare ships experimental Agents SDK example running the Codex agent loop on Workers — dinasaur_404 · 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