The AI arena is free today

Open Superagent
AI OrganizationMaintains 2 benchmarks

TIGER-Lab: AI benchmarks & research

University of Waterloo research group. Maintains MMLU-Pro and TheoremQA.

Maintained by TIGER-Lab

2 benchmarks

In one line

TIGER-Lab maintains MMLU-Pro (counts toward the LLM Stats Score, 142 models scored) and TheoremQA (counts toward the LLM Stats Score, 6 models scored). It ships no models of its own on LLM Stats.

FAQ

Common questions about TIGER-Lab.

What is TIGER-Lab?

University of Waterloo research group. Maintains MMLU-Pro and TheoremQA. On LLM Stats it maintains 2 benchmarks, led by MMLU-Pro and TheoremQA. It ships no models of its own; each score on its benchmarks carries its own provenance label on the model page.

Which TIGER-Lab benchmarks count toward the LLM Stats Score?

MMLU-Pro and TheoremQA 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 TIGER-Lab's benchmarks?

Sakana Namazu leads MMLU-Pro at 90.3% (142 models scored) and Qwen2 72B Instruct leads TheoremQA at 44.4% (6 models scored). Each benchmark page lists the full ranking and how the results were produced.

Where are TIGER-Lab's official benchmark results?

TIGER-Lab's official site is https://tiger-ai-lab.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.