Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains

A new benchmark called Relay-Bench, introduced in arXiv:2607.18438v1, measures large language models' ability to complete multi-domain reasoning chains in a single prompt, with the leading model GPT-5.5 (xHigh) scoring 43.3%. The benchmark consists of composite problems combining two to thirteen subproblems from domains including visual reasoning, coding, math, information extraction, problem-solving, general knowledge, and data analysis, without requiring multi-modal input or output.

arXiv:2607.18438v1 Announce Type: new Abstract: Introducing Relay-Bench, an unsaturated, holistic, text-only benchmark that measures LLMs' ability to complete an assortment of tasks from distinct domains in a single prompt. The leading model, GPT-5.5 xHigh , scores 43.3%. The test set entirely consists of composite problems: groups of single-domain subproblems that are strung together into challenges that require reasoning across multiple domains in combination. Many of these problems then have layers of complexity added through prompt encoding and deliberate context bloat. Domains tested include visual reasoning, coding, math, information extraction with a focus on web search , problem-solving, general knowledge, and data analysis. No restrictions are imposed outside of the model harness, and models are explicitly encouraged to leverage code-execution, web searches, and all available tools. All problems are composed of two to thirteen subproblems and do not require multi-modal input or output.