The AI arena is free today

Open Superagent
AI OrganizationMaintains 2 benchmarks

HKUST NLP: AI benchmarks & research

Hong Kong University of Science and Technology NLP group. Maintains Toolathlon.

Maintained by HKUST NLP

2 benchmarks

In one line

HKUST NLP maintains Toolathlon (counts toward the LLM Stats Score, 42 models scored) and Toolathlon-Verified (counts toward the LLM Stats Score, 6 models scored). It ships no models of its own on LLM Stats.

FAQ

Common questions about HKUST NLP.

What is HKUST NLP?

Hong Kong University of Science and Technology NLP group. Maintains Toolathlon. On LLM Stats it maintains 2 benchmarks, led by Toolathlon and Toolathlon-Verified. It ships no models of its own; each score on its benchmarks carries its own provenance label on the model page.

Which HKUST NLP benchmarks count toward the LLM Stats Score?

Toolathlon and Toolathlon-Verified count toward the LLM Stats Score. Only benchmarks admitted to the core set move the main leaderboard; the rest are shown for transparency.

Which models lead HKUST NLP's benchmarks?

GLM-5.3-Flash leads Toolathlon at 78.4% (42 models scored) and Claude Opus 5.5 leads Toolathlon-Verified at 77.8% (6 models scored). Each benchmark page lists the full ranking and how the results were produced.

Where are HKUST NLP's official benchmark results?

HKUST NLP's official site is https://hkust-nlp.github.io. Each benchmark page on LLM Stats links to that benchmark's own paper or leaderboard, and shows the scores next to every other benchmark so models can be compared on one page.