AI IntelligenceOct 29, 2026Practical Tip
Article
Ted Sanders says LLM performance is multidimensional, but much variation is explained by model size
Bigger models are generally more performant/reliable, cost more per token, and have better recall of esoteric facts.
AI-generated: summaries written by AI from the linked sources. How we use AI
AI-generatedSource: Simon Willison
01
Source Brief
Ted Sanders says LLM performance is multidimensional, but much variation is explained by model size: bigger models are generally more performant/reliable, cost more per token, and have better recall of esoteric facts.
02
Practical Tip
When choosing a model, treat size as a rough proxy: expect larger models to be more reliable and better at esoteric recall but costlier per token, so match model size to task difficulty and budget.
03