# Toolathlon-Verified — AI model rankings

Tests how well the AI uses everyday personal tools and apps to get things done — a human-checked version of Toolathlon. Higher is better.

9 tracked models have a published Toolathlon-Verified score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | GLM-5.3-Flash | Z.ai | 78.4% | Lab | Aug 26 2026 |
| 2 | Muse Spark 1.1 | Meta | 75.6% | Lab | Jul 9 2026 |
| 3 | DeepSeek-V4-Pro-0813 | DeepSeek | 74.1% | Lab | Aug 13 2026 |
| 4 | Qwen3.8-Flash-Next | Qwen | 73.5% | Lab | Aug 26 2026 |
| 5 | Qwen3.8-Max-0902 | Qwen | 73.3% | Lab | Sep 2 2026 |
| 6 | Kimi K3 | Moonshot AI | 73.2% | Lab | Jul 16 2026 |
| 7 | Qwen3.8-Max | Qwen | 72.5% | Lab | Aug 3 2026 |
| 8 | DeepSeek-V4-Flash-0731 | DeepSeek | 70.3% | Lab | Jul 31 2026 |
| 9 | Muse Spark | Meta | 49.4% | Lab | Apr 8 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/toolathlon-verified
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.