General tool use

Toolathlon

Tests how well the AI uses everyday real-world tools and apps to get things done. Higher is better.

Rankings

Higher is better

Toolathlon — frequently asked questions

What is Toolathlon?
Tests how well the AI uses everyday real-world tools and apps to get things done. Higher is better.
Which AI model scores highest on Toolathlon?
Gemini 3.5 Flash by Google holds the best Toolathlon result among tracked models, at 56.5% (released May 19 2026). Higher scores are better on this benchmark.
What are the top 5 models on Toolathlon?
1. Gemini 3.5 Flash (Google) — 56.5%; 2. GPT-5.5 (OpenAI) — 55.6%; 3. GPT-5.4 (OpenAI) — 54.6%; 4. Gemini 3.0 Flash (Google) — 49.4%; 5. Gemini 3.1 Pro (Google) — 48.8%.
How many models have a published Toolathlon score?
5 tracked models have a published Toolathlon score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.
← All benchmarks