#pass-at-k
-
LLM Benchmarks Explained: MMLU, HumanEval, GSM8K
What MMLU, HumanEval and GSM8K actually contain, how each score is computed, and the point where a headline benchmark number stops being useful.
-
LLM Eval Frameworks Compared: Pick the Right One
A comparison of lm-evaluation-harness, OpenAI Evals, HELM, Inspect, promptfoo, DeepEval and Ragas, with the task shapes each harness actually fits.
-
LLM Evaluation Design: From Task to Regression Suite
How to design an LLM evaluation: task-grounded eval sets, grader choice, sampling variance, and the contamination traps that mislead benchmark scores.