event

LLMs Efficiency Comparison

5 items · started 2026-09-28 · closed 2026-10-02

  1. Sonnet 5.5 is really a very good model, especially in its capabilities or intelligence, although the price is a bit expensive, but really don't care about the price. Quality is far more valuable than quantity.

  2. https://preview.redd.it/5ma6jpa82nsh1.png?width=971&format=png&auto=webp&s=f3eab962fdeaa4f2d3eb02cd4a6c78c5e7cad873 I have an OpenCode Go and Cursor Plus ($20) subscription. Cursor just added 5.3 and 5.3 flash, and I was thinking of moving…

  3. I know this benchmark is saturated, but it is still useful to see how efficient different models can complete the questions and WOW does Sonnet pick up the slack from the older Sonnet. It is also worth noting that the only top models that…

  4. I built jevpipe as a wrapper for TypeSafe's Jev System 1 model. Jev answers yes/no, picks from a few choices or gives a score, with probabilities, and it's fast and cheap.

  5. OpenCode@opencodeOperation Cheepseek Phase 2: $60 of usage for DeepSeek v4.1 Flash is now permanent enjoy :)3:22 PM · Sep 25, 2026·140.8KViews2562015.1K538 OpenCode@opencodeOperation Cheepseek Phase 2: $60 of usage for DeepSeek v4.1 Flash…

← all threads