Ask HN: What LLM models are you using and why?
Hello, HN!
I'm wondering what y'all are using for your daily driver these days and why?
I've found myself using GPT-5.5 more than Opus 4.7 for work; which, has been a pretty big reversal. Previously, I was using Opus 4.6 for everything, and GPT-5.4 was only ever in the picture to provide a second opinion (with Grok a distant 3rd only when I wanted to throw some "chaos" into the mix). The reason I've personally pivoted, is I've found GPT-5.5 to be a bit more consistent, predictable, and tends to write in a way I find less tiresome (even if the code isn't quite as good as Opus 4.7).
For personal projects, I've started experimenting with DeepSeek V4 and have been pretty blown away by it because of it's cost to quality and I've found the 1M token window to be incredibly helpful for long-running tasks. Though I may also have an over abundance of fear of compaction during tasks. DeepSeek isn't quite as good at one-shotting things as either GPT-5.5 or Opus-4.7, but with sufficient linter/static-analysis guardrails I've found it's really hard to complain or find faults (especially at the price).
Finally, if you're also making use of reranking and/or embedding models, or anything else, to augment or perform specific tasks please share those too! 1. gpt-5.5-medium for most demanding coding tasks. 2. gpt-5.3-codex-medium for genrally most of the other coding tasks. 3. deepseek-v4-flash for heavy agentic research/loops (non-coding related). 4. mimo-v2.5-pro for crunching/summarizing large texts. 5. gemini-3.1-flash-lite for image understanding. 6. opus-4.7 very occasionally when gpt-5.5 fails, or vice-versa, and sonnet-4.6 when codex-5.3 fails. 7. deepseek-v4-pro when I need to do a long agentic session, and want higher quality, for cheap (non-coding). 8. perplexity/pplx-embed-v1-0.6b for embeddings, via openrouter. Just curious what constitutes a 'demanding' coding task for you. I use Opus 4.7 for personal stuff (basically for everything), but have been considering gpt-5.5 given all I hear about it. At work I use 4.6 because we don't have 4.7 yet...zzz... I also do a LOT of personal/portfolio work with self-hosted models. Ministral-3-14B-Reasoning for validating concepts, MVPs, etc and some prod systems (punches above its weight class).
Qwen3.6-35B-A3B for self-hosted coding (custom harness).
GPT-OSS-120B for self-hosted coding or more reasoning-intensive agentic flows.
Qwen3.5-122B-A10B currently in evals for agentic coding. For straightforward coding tasks I use gpt-5.3-codex on high or xhigh. Sometimes I try 5.5 but overall 5.3-codex is more than capable enough for most of my needs and quite a bit cheaper. For more interactive/discussion/planning or orchestration stuff, I find myself going back and forth between Opus 4.7 and GPT 5.5. Still not sure which one I prefer. I only use Anthropic models. Haven't touched GPT for a long time after I found myself swearing at them. Opus 4.7, or 4.6 where it's still available at work: For spec'ing up projects or changes. The 15x multiplyer on Copilot means I rarely do this. Sonnet 4.6 everywhere else. It rarely fails me. GPT-5.5 + Opus-4.7 here. Codex for pure coding task with clear goal, claude code for the rest. Also combined with opencode to experiment new models. fyi: I didn't have much lock on Deepseek v4 pro, with opencode + openrouter it's incredibly slow. How did op did it? GPT 5.5 main
opus 4.7 frontend and when i need something different
kimi 2.6 and GLM 5.1 when i don't have to pay on the task (using the opencode go subscription) Claude Sonnet for daily tasks, GPT 5.5 for reviewing Sonnet’s work, and Qwen for very specific tasks GPT-5.5 daily.Opus for hard stuff.Deep seek for long context+ cheap iteration.Everthing else is routing and tool now. By default, I use Sonnet 4.6, and if Sonnet 4.6 fails, I use Opus 4.7. GPT-5.5 for daily ideas and brainstorming. It has become my daily go to. Opus 4.6. Does the job. Not much of an experimenter. for idea using gpt3.5,claude for coding and also impressed by deepseek it large context window is really useful for long projects. Opus 4.7 in Vscode via Claude Code. qwencodernext. ask me about what it does and doesnt do. opus 4.7