GPT-5.5 (xHigh)

mentions 2 type Person feed RSS

// recent coverage 2 mentions

22:10

2026-07-26

arxiv.org

large-language-models

Frontier LLMs drop from 83% to 43% once reasoning has to chain across domains

A new benchmark called Relay-Bench shows that frontier large language models (LLMs) drop from an average of 83% on single-domain tasks to 43% when required to chain reasoning across multiple domains i…

04:00

2026-07-22

machinebrief.com

large-language-models

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…

// co-occurs with top 2 entities

Relay-Bench 2 arXiv 2

// topics top 3 topics

large language models 2 ai research 2 artificial intelligence 1