HumanEval
Code-generation benchmark: 164 problems with hidden unit tests, scored by whether the generated code passes.
A coding benchmark of 164 hand-written Python problems with hidden unit tests. Measures functional correctness by running the generated code rather than string-matching. Pass@1 / pass@10 are reported.
In practice
Default benchmark for coding ability. Interviews probe pass@k semantics and why teams supplement with MBPP and live benchmarks like SWE-bench.
Related topics
Related terms
Hallucination
When a model confidently makes up something that isn't true.
LLM Evaluation
Measuring whether an LLM does what you want, beyond "looks fine to me".
Perplexity
Exp(average cross-entropy) on held-out text; lower means the model is less surprised by real data.
Reasoning Model
An LLM trained to reason at length internally before answering. Slower and more expensive, but much better on hard problems.
Guardrails
Pre- and post-processing layers that block bad inputs/outputs and enforce policy on top of an LLM.
MMLU (Massive Multitask Language Understanding)
Multiple-choice benchmark across 57 academic subjects; the standard "raw knowledge" headline number.