A Challenging, Contamination-Free LLM Benchmark.

a benchmark designed to assess the performance of multimodal web agents on realistic visually grounded tasks.

benchmark designed to evaluate large language models (LLMs) on solving complex, college-level scientific problems from domains like chemistry, physics, and mathematics.

a large-scale question-answering benchmark focused on real-world financial data, integrating both tabular and textual information.

a benchmark evaluating QA methods that operate over a mixture of heterogeneous input sources (KB, text, tables, infoboxes).

An Automatic Evaluator for Instruction-following Language Models using Nous benchmark suite.