Comprehensive rankings for LLMs, benchmarks, and model comparisons. Access intelligence, coding, and agentic indices for 1000+ models.
View Leaderboard APIRanked by Intelligence Index, then Advanced Coding capability. Models without verified scores excluded.
OpenRouter unified benchmarks including GPQA, Tau-bench, Design Arena, and Artificial Analysis.
Side-by-side comparison of model specs, pricing, and benchmark scores.
/api/v1/leaderboard
Main leaderboard ranked by intelligence
/api/v1/benchmarks
Benchmark evaluation matrix
/api/v1/models
Query and filter all models
/api/v1/providers
List of AI providers
/api/v1/health
System health check