What does the Pareto frontier mean here?

A model is on the frontier if no other model is both cheaper and higher quality. Frontier models represent the best available trade-offs; a model off the frontier is "dominated" because you could get equal or better quality for the same or less money.

Which quality metric should I use?

Match it to your task. MMLU reflects broad knowledge and reasoning, HumanEval measures coding ability, and MT-Bench captures conversational quality. A model that tops one metric may sit mid-pack on another, so pick the one that mirrors your workload.

Should I always pick a frontier model?

Usually yes — off-frontier models are strictly worse value. Among frontier models, pick the cheapest one that clears your minimum quality bar; paying for more quality than you need is wasted budget.

Are the benchmark scores exact?

They are approximate published benchmark figures used as editable presets. Benchmarks vary by prompt and version and can be gamed, so treat them as a guide, not gospel, and validate on your own task.

Is anything sent to a server?

No. The plot and frontier are computed in your browser from a built-in table. Nothing is uploaded.

Inference Cost vs Quality Frontier Explorer

See the cost-quality trade-off at a glance

Choosing an LLM is a trade-off between price and capability. This explorer plots major models with cost per 1M tokens against a benchmark quality score, then highlights the Pareto frontier — the models that give the most quality for their cost. Everything below the frontier is a worse deal.

How the frontier works

A model is Pareto-optimal if no other model beats it on both axes at once — that is, nothing else is simultaneously cheaper and higher quality:

dominated(A) = exists B such that cost(B) <= cost(A)
                                  and quality(B) >= quality(A)
                                  and B != A
frontier = models that are not dominated

The frontier traces the efficient trade-off curve. Picking off the frontier means you are leaving quality or money on the table — there is a strictly better model available.

Tips for using the plot

Pick the cheapest frontier model above your quality bar. Set the minimum quality you need, then take the least expensive model that clears it.
Switch metrics to match the job. A coding workload should rank on HumanEval, not MMLU — the frontier reshapes per metric.
Validate on your own task. Public benchmarks guide the shortlist; your actual prompts decide the winner.