Частые вопросы

We compute a composite score from multiple benchmark results including MMLU, GPQA, SWE-Bench, HumanEval, AIME, and Arena ELO.

We update benchmark scores and pricing data on a weekly basis. Major model releases trigger an immediate update cycle.

Scores come from official benchmark leaderboards and independent evaluations. Pricing data comes directly from provider APIs.

The composite score is a weighted average of all tracked benchmark results for a model.

Yes! Visit our Compare page to select up to 4 models and see a side-by-side breakdown of all metrics.

Arena ELO is a crowd-sourced preference ranking from LMSYS Chatbot Arena, where humans compare model outputs side-by-side in blind tests.