Personal tool use
Toolathlon-Verified
Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better.
Rankings
Higher is betterToolathlon-Verified — frequently asked questions
- What is Toolathlon-Verified?
- Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better.
- Which AI model scores highest on Toolathlon-Verified?
- Muse Spark 1.1 by Meta holds the best Toolathlon-Verified result among tracked models, at 75.6% (released Jul 9 2026). Higher scores are better on this benchmark.
- What are the top 5 models on Toolathlon-Verified?
- 1. Muse Spark 1.1 (Meta) — 75.6%; 2. DeepSeek-V4-Pro-0813 (DeepSeek) — 74.1%; 3. Kimi K3 (Moonshot AI) — 73.2%; 4. DeepSeek-V4-Flash-0731 (DeepSeek) — 70.3%; 5. Muse Spark (Meta) — 49.4%.
- How many models have a published Toolathlon-Verified score?
- 5 tracked models have a published Toolathlon-Verified 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.