'%20d='M69.364%2019.146c36.687%2027.806%2076.147%2084.186%2090.636%20114.439%2014.489-30.253%2053.948-86.633%2090.636-114.439C277.107-.917%20320-16.44%20320%2032.957c0%209.865-5.603%2082.875-8.889%2094.729-11.423%2041.208-53.045%2051.719-90.071%2045.357%2064.719%2011.12%2081.182%2047.953%2045.627%2084.785-80%2082.874-106.667-44.333-106.667-44.333s-26.667%20127.207-106.667%2044.333c-35.555-36.832-19.092-73.665%2045.627-84.785-37.026%206.362-78.648-4.149-90.071-45.357C5.603%20115.832%200%2042.822%200%2032.957%200-16.44%2042.893-.917%2069.364%2019.147Z'/%3e%3c/svg%3e)
This is less interesting to me for the winners (it's a content site, so no surprise Astro and htmx win most of them). It's that frameworks beat vanilla every time. This backs up my observations that LLMs are better with frameworks. It stops them burning tokens reinventing the wheel each time.
Sébastien Chopin@atinux.com
Nolan Lawson benchmarked the AI cost of JS frameworks (data, not vibes). @nuxt.com looks great for the agentic era: - Fewest tokens (even less than vanilla JS) - Near-top cost + time per run - 2nd-fewest LOC to maintain Cheapest code is what the agent never writes. nolanlawson.com/2026/10/28/...
nolanlawson.com