ToolMaze - Clean Task Success: leaderboard
Metric: Task success rate (%) with no tool failure injected, 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 December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 77 |
| 2 | GLM-5.1 | 75.75 |
| 3 | Gemini 3.1 Pro (Preview) | 71.25 |
| 4 | GPT-5.5 | 70 |
| 5 | DeepSeek V4 Pro | 69.75 |
| 6 | MiniMax-M2.7 | 56.5 |
| 7 | Qwen 3.6 27B | 42.25 |
| 8 | Qwen 3.5 397B A17B | 42 |
| 9 | Qwen 3.5 35B A3B | 41.5 |
Interactive version: theaggregate.ai/benchmark?slug=toolmaze-clean-task-success · How It Works · Data refreshed daily, snapshot 2026-09-29.