The AI arena is free today

Open Superagent
AI OrganizationMaintains 2 benchmarks

Abacus.AI: AI benchmarks & research

AI platform company. Maintains LiveBench with NYU.

Maintained by Abacus.AI

2 benchmarks

In one line

Abacus.AI maintains LiveBench (counts toward the LLM Stats Score, 38 models scored) and LiveBench 20241125 (counts toward the LLM Stats Score, 15 models scored). It ships no models of its own on LLM Stats.

FAQ

Common questions about Abacus.AI.

What is Abacus.AI?

AI platform company. Maintains LiveBench with NYU. On LLM Stats it maintains 2 benchmarks, led by LiveBench and LiveBench 20241125. It ships no models of its own; each score on its benchmarks carries its own provenance label on the model page.

Which Abacus.AI benchmarks count toward the LLM Stats Score?

LiveBench and LiveBench 20241125 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 Abacus.AI's benchmarks?

o3-mini leads LiveBench at 84.6% (38 models scored) and Qwen3 VL 235B A22B Thinking leads LiveBench 20241125 at 79.6% (15 models scored). Each benchmark page lists the full ranking and how the results were produced.

Where are Abacus.AI's official benchmark results?

Abacus.AI's official site is https://abacus.ai. 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.