NIH/Multi-needle

Multi-needle in a haystack benchmark for evaluating long-context comprehension capabilities of language models by testing retrieval of multiple target pieces of information from extended documents

Llama 3.2 3B Instruct from Meta currently leads the NIH/Multi-needle leaderboard with a score of 0.847 across 1 evaluated AI models.

Paper

MetaLlama 3.2 3B Instruct leads with 84.7%.

Progress Over Time

Interactive timeline showing model performance evolution on NIH/Multi-needle

State-of-the-art frontier
Open
Proprietary

NIH/Multi-needle Leaderboard

1 models
ContextCostLicense
13B
Notice missing or incorrect data?

FAQ

Common questions about NIH/Multi-needle.

What is the NIH/Multi-needle benchmark?

Multi-needle in a haystack benchmark for evaluating long-context comprehension capabilities of language models by testing retrieval of multiple target pieces of information from extended documents

What is the NIH/Multi-needle leaderboard?

The NIH/Multi-needle leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Llama 3.2 3B Instruct by Meta leads with a score of 0.847. The average score across all models is 0.847.

What is the highest NIH/Multi-needle score?

The highest NIH/Multi-needle score is 0.847, achieved by Llama 3.2 3B Instruct from Meta.

How many models are evaluated on NIH/Multi-needle?

1 models have been evaluated on the NIH/Multi-needle benchmark, with 0 verified results and 1 self-reported results.

Where can I find the NIH/Multi-needle paper?

The NIH/Multi-needle paper is available at https://arxiv.org/abs/2406.11230. The paper details the methodology, dataset construction, and evaluation criteria.

What categories does NIH/Multi-needle cover?

NIH/Multi-needle is categorized under long context. The benchmark evaluates text models.

More evaluations to explore

Related benchmarks in the same category

View all long context
nolima
long context
44 models
LVBench

LVBench is an extreme long video understanding benchmark designed to evaluate multimodal models on videos up to two hours in duration. It contains 6 major categories and 21 subcategories, with videos averaging five times longer than existing datasets. The benchmark addresses applications requiring comprehension of extremely long videos.

long contextmultimodal
20 models
LongBench v2

LongBench v2 is a benchmark designed to assess the ability of LLMs to handle long-context problems requiring deep understanding and reasoning across real-world multitasks. It consists of 503 challenging multiple-choice questions with contexts ranging from 8k to 2M words across six major task categories: single-document QA, multi-document QA, long in-context learning, long-dialogue history understanding, code repository understanding, and long structured data understanding.

long context
14 models
AA-LCR

Agent Arena Long Context Reasoning benchmark

long context
13 models
MRCR v2 (8-needle)

MRCR v2 (8-needle) is a variant of the Multi-Round Coreference Resolution benchmark that includes 8 needle items to retrieve from long contexts. This tests models' ability to simultaneously track and reason about multiple pieces of information across extended conversations.

long context
10 models
EgoSchema

A diagnostic benchmark for very long-form video language understanding consisting of over 5000 human curated multiple choice questions based on 3-minute video clips from Ego4D, covering a broad range of natural human activities and behaviors

long contextvideo
9 models