Counting-Stars: A Multi-evidence, Position-aware, and Scalable Benchmark for Evaluating Long-Context Large Language Models

While recent research endeavors have focused on developing Large Language Models (LLMs) with robust long-context capabilities, due to the lack of long-context benchmarks, relatively little is known about how well the performance of long-context LLMs. To address this gap, we propose a multi-evidence, position-aware, and scalable benchmark for evaluating long-context LLMs, named Counting-Stars, which evaluates long-context LLMs by using two tasks: multi-evidence acquisition and multi-evidence reasoning. Based on the Counting-Stars test, we conduct experiments to evaluate long-context LLMs (i.e., GPT-4 Turbo, Gemini 1.5 Pro, Claude3 Opus, GLM-4, and Moonshot-v1). Experimental results demonstrate that Gemini 1.5 Pro achieves the best overall results, while the performance of GPT-4 Turbo is the most stable across various tasks. Furthermore, our analysis of these LLMs, which are extended to handle long-context scenarios, indicates that there is potential for improvement as the length of the input context and the intricacy of the tasks are increasing.