Topic: benchmark

Latest on “benchmark”

The AI news that matters for people who make things — what happened, and how to put it to work in Grafy.

arXiv Computation and Language3 h ago4 min read

GraphNIAH benchmark reveals LLM limits on long‑context graph reasoning

A new GraphNIAH benchmark shows that top‑tier LLMs struggle with multi‑hop reasoning over real citation graphs, highlighting gaps in long‑context capabilities.

Try in Graphgraphbenchmarklong-contextllm

arXiv AI2 days ago5 min read

FilingLoop Benchmark Shows Self‑Evolving LLM Agents Improve SEC Filing Review

Researchers unveil FilingLoop, an interactive benchmark for LLM agents that review SEC filings.

Try in Readerllmbenchmark

arXiv AI6 days ago5 min read

AgentOrch Benchmark Shows Global Orchestration Closing Gap to Step‑by‑Step AI Agents

The new AgentOrch benchmark compares global orchestration with step‑by‑step LLM agents.

Try in Readeragent orchestrationllm agents