Authoritative Sources
Ranking data is collected from public leaderboards such as LMSYS Arena, SWE-bench, MATH, MMMU, LiveBench, and pricing catalogs.
AI Model Rankings
Browse and compare AI models with detailed rankings across multiple domains
Evaluation Methodology
AITier combines public benchmark rankings, normalized scores, freshness metadata, and provider coverage to make model selection easier.
Comparable Scores
Scores are normalized per domain so models can be compared inside the same task category without mixing incompatible benchmarks.
Freshness First
Each row keeps source update time where available, and newer observations are preferred when duplicate model entries exist.