# Emergent Abilities and Benchmark Evolution

Large models show surprising capabilities that scale with size. This sub-article expands [Section 1 and 8 of Recent Topics](../recent.md) and [Large Language Models](large-language-models.md).

## Emergent Abilities
- Some tasks appear only at certain model scales (e.g., in-context learning, arithmetic, instruction following).
- Debate: are these truly emergent or predictable given data/compute?

## Benchmark Saturation
- Models exceed old benchmarks, prompting harder evaluations.
- Leaders saturate MMLU, HumanEval, ARC; new evals test reasoning, safety, and real-world use.

## Evaluation Challenges
- Benchmarks can be gamed; contamination is a concern.
- Capability ≠ alignment; evaluation must track both.

## Why It Matters
Understanding emergence helps forecast capability and design oversight.

## Sources
- Wei, J. et al. (2022). *Emergent Abilities of Large Language Models.*
- OpenAI. *Frontier evaluations.*

*Back to [Recent Topics](../recent.md).*