Back to Benchmarks
📜

RULER

RULER Benchmark

Reasoning over long context (not pure retrieval), most production-realistic

📜 Long Context
Best: 82%
2 Models Evaluated
Champion

Gemini 3 Pro

Google

82%

Best Score

Model Rankings

All models ranked by score on RULER. Scores are relative to the best score of 82%.

#ModelProviderScorevs Best
1Gemini 3 Pro
Elo 1486
Google
82%
Best
2Claude Opus 4.6
Elo 1503
Anthropic
56%
-26.0%

Score Distribution

Gemini 3 Pro
82%
Claude Opus 4.6
56%

Run This Benchmark

Learn how to evaluate your own models on RULER.

RULER is a standardized benchmark for evaluating AI model capabilities.

To run this benchmark on your own models, visit the official benchmark page or leaderboard for detailed instructions, code, and evaluation scripts.

Data compiled from official model cards, public leaderboards, and independent evaluations.