← 🤖 Algorithms & AI

📊 LLM Evaluation & Benchmarks

Leader:
95% CI: ± 0.0 pts
FPS:
Benchmarks
MMLU (knowledge)
HumanEval (code)
BIG-Bench (reasoning)
Chatbot Arena (Elo)
Drag — rotate · Scroll — zoom

📊 LLM Evaluation & Benchmarks — Simulating How Leaderboards Work

This simulation turns LLM benchmarking into something you can watch happen: six model bars rise and fall across four benchmark columns — MMLU, HumanEval, BIG-Bench and Chatbot Arena — as sampling noise and benchmark weighting change the leaderboard in real time.

🔬 What It Demonstrates

Each bar's observed score is the model's underlying skill plus random noise drawn from a normal distribution with standard error SE = σ/√n. Small benchmarks like HumanEval (only 164 problems) have a much noisier score than large ones like MMLU (about 14,000 questions) — the white whisker on top of each bar shows the resulting 95% confidence interval, and it visibly shrinks as you raise the sample size.

🎮 How to Use

Drag Sample size n to see how more test items narrow the confidence interval, Task noise σ to make individual questions harder to grade consistently, and Weight: code ↔ knowledge to shift the composite leaderboard between knowledge/reasoning benchmarks and code/human-preference benchmarks. Press Reroll sample to redraw a fresh evaluation run, or Reset to return to the defaults.

💡 Did You Know?

Real leaderboards are sensitive to exactly this kind of weighting: a model can rank #1 on a code-heavy composite and drop several places on a knowledge-heavy one, which is why serious evaluation suites like HELM report many benchmarks side by side instead of collapsing everything into one score.