Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models
This benchmark addresses the need for more rigorous evaluation of LLMs' problem-solving abilities in complex, domain-specific reasoning tasks, though it is incremental as it builds on existing benchmarking efforts.
The authors introduced JEEBench, a challenging benchmark of 515 pre-engineering problems from the IIT JEE-Advanced exam, and found that even advanced LLMs like GPT-4 achieve less than 40% accuracy despite using techniques like self-consistency and chain-of-thought prompting.
The performance of large language models (LLMs) on existing reasoning benchmarks has significantly improved over the past years. In response, we present JEEBench, a considerably more challenging benchmark dataset for evaluating the problem solving abilities of LLMs. We curate 515 challenging pre-engineering mathematics, physics and chemistry problems from the highly competitive IIT JEE-Advanced exam. Long-horizon reasoning on top of deep in-domain knowledge is essential for solving problems in this benchmark. Our evaluation on various open-source and proprietary models reveals that the highest performance, even after using techniques like self-consistency, self-refinement and chain-of-thought prompting, is less than 40%. The typical failure modes of GPT-4, the best model, are errors in algebraic manipulation, difficulty in grounding abstract concepts into mathematical equations accurately and failure in retrieving relevant domain-specific concepts. We also observe that by mere prompting, GPT-4 is unable to assess risk introduced by negative marking for incorrect answers. For this, we develop a post-hoc confidence-thresholding method over self-consistency, which enables effective response selection. We hope that our challenging benchmark will guide future re-search in problem-solving using LLMs.