Competitive Benchmarking

Arena

LLM leaderboard — benchmarks, latency, pricing, and community rankings.

Live Leaderboard

#ModelEloTrend

Click a model to see details. Click a second model to compare.

Human Preference Index

94.2

Aggregate Score

Based on human preference votes across all benchmark categories.

vs. last month +2.1

Recent Head-to-Head

Avg. Latency

Avg. Latency

Community votes

Votes

Safety Score

Value score