RULER
RULER v1 is a synthetic long-context benchmark for measuring how model quality degrades as input length increases. This packaging follows the public standalone NVIDIA RULER implementation with 13 official tasks spanning retrieval, multi-hop tracing, aggregation, and QA.
Nemotron 3 Super (120B A12B) from NVIDIA currently leads the RULER leaderboard with a score of 0.917 across 3 evaluated AI models.
Nemotron 3 Super (120B A12B) leads with 91.8%, followed by 
Phi-3.5-MoE-instruct at 87.1% and Phi-3.5-mini-instruct at 84.1%.
Progress Over Time
Interactive timeline showing model performance evolution on RULER
RULER Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | 120B | — | — | |||
| 2 | Microsoft | 60B | — | — | ||
| 3 | Microsoft | 4B | — | — |
FAQ
Common questions about RULER.
Sub-benchmarks
RULER 1000K
RULER 1000K evaluates the official 13-task RULER v1 suite at a 1048576-token (1M) context budget.
RULER 128k
RULER 128k evaluates the official 13-task RULER v1 suite at a 131072-token context budget.
RULER 16k
RULER 16k evaluates the official 13-task RULER v1 suite at a 16384-token context budget.
RULER 2048K
RULER 2048K evaluates the official 13-task RULER v1 suite at a 2097152-token (2M) context budget.
RULER 32k
RULER 32k evaluates the official 13-task RULER v1 suite at a 32768-token context budget.
RULER 4k
RULER 4k evaluates the official 13-task RULER v1 suite at a 4096-token context budget.
RULER 512K
RULER 512K evaluates the official 13-task RULER v1 suite at a 524288-token context budget.
RULER 64k
RULER 64k evaluates the official 13-task RULER v1 suite at a 65536-token context budget.
RULER 8k
RULER 8k evaluates the official 13-task RULER v1 suite at an 8192-token context budget.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions