ToolMaze: leaderboard
Metric: Composite score (%): mean of task success over the clean and four perturbed settings, perturbation recovery rate, and one minus recovery cost, each macro-averaged over the four topology levels; 400 DAG-structured tool-use tasks (four topology levels) over 270 tools, each also run under four injected tool-failure modes (explicit or implicit, transient or permanent); sandboxed, 25 agent steps, temperature 1, the standard tool-use prompt; higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Pro | 36.33 |
| 2 | GPT-5.5 | 35.94 |
| 3 | GLM-5.1 | 32.28 |
| 4 | Gemini 3.1 Pro (Preview) | 32.19 |
| 5 | Qwen 3.5 397B A17B | 31.64 |
| 6 | Qwen 3.5 35B A3B | 31.55 |
| 7 | Qwen 3.6 27B | 29.65 |
| 8 | Claude Sonnet 4.6 | 27.35 |
| 9 | MiniMax-M2.7 | 25.03 |
Interactive version: theaggregate.ai/benchmark?slug=toolmaze · How It Works · Data refreshed daily, snapshot 2026-09-29.