Writing tagged benchmark

2 Construct resources on benchmark.

Resources tagged benchmark

  1. The best cheap LLM for AI agents: 11 setups through our production agent loop

    article · Nov 10, 2026 · Ankush

    We ran 11 cheap model setups through Construct's agent loop on 11 real tasks: pass rate, cost per passed task and speed for GLM, DeepSeek, Gemini, Qwen and Kimi.

  2. Clef beat Jev on Jev's home turf

    article · Oct 5, 2026 · Ankush

    We ran Cloudflare's Clef and Clef-flash against Jev on five production AI agent decisions: 1,053 calls, accuracy, determinism, drift, cost, and what we are switching.