Deep dive
Best LLM for coding: November 2026 benchmarks, compared
The best LLM for coding as of November 2026, by situation: agents, value, large repos, local hardware. Dated scores and who ran each benchmark.
15 min readCoding agents
Topic
Model releases
New models from frontier labs and open-weight releases, read for what changes for developers: context length, pricing, tool use, and license.
Frontier and open-weight models06 articles04 glossary terms08 platforms
Articles
Read on this topic
Deep dives and guides filed under this topic, newest first.
All articlesGuide
Claude API pricing: caching, batch, and real bills
Claude API pricing for every current model as of November 8, 2026, with cache break-even math, batch stacking, tool fees, and a tested cost calculator.
14 min readAPIs and pricing
Guide
Gemini API pricing: free tier, caching, and real bills
Gemini API pricing for every current model as of November 8, 2026: free versus paid, cache storage math, batch, grounding, thinking, and a tested calculator.
16 min readAPIs and pricing
Guide
LoRA fine tuning: QLoRA, r, alpha, and a tested PEFT script
LoRA fine tuning from the paper to serving: r, alpha, QLoRA, dataset format, and a PEFT script run on CPU with real output, adapter size, and evals.
12 min readFine-tuning and training
Deep dive
Mixture of experts: how MoE works and what it costs
Mixture of experts LLMs load every expert but run only a few per token. Compare total and active parameters, and see what memory, batching, and routing cost.
11 min readModel releases
Deep dive
vLLM vs SGLang, plus Ollama and llama.cpp compared
vLLM vs SGLang compared on prefix caching, hardware, and constrained decoding, plus Ollama and llama.cpp. Every default checked November 8, 2026.
12 min readInference and serving
Glossary
Terms you will meet
- Mixture of expertsMoE
- Mixture of experts (MoE) is a model architecture that replaces selected feed-forward layers with many expert sub-networks and routes each token to only a few of them. Total parameters can be very large while the compute per token stays close to that of a much smaller dense model.
- Reasoning model
- A reasoning model is a model trained to generate intermediate reasoning tokens before its final answer. It trades latency and output tokens for better results on math, code, and multi-step problems.
- Small language model
- A small language model is a language model small enough to run on a single consumer GPU, a laptop, or a phone, usually under about 10 billion parameters. It suits narrow tasks, low latency, and keeping data on the device.
- Transformer
- A transformer is the neural network architecture behind modern LLMs, introduced in the 2017 paper Attention Is All You Need (Vaswani et al.). It stacks attention and feed-forward layers and processes all tokens of the input in parallel.
Platforms