ToolMaze - Perturbation Recovery Rate: leaderboard
ToolMaze (2026) tests tool-using LLM agents on 400 DAG-structured tasks over 270 tools, each also run with injected tool failures that are explicit or implicit and transient or permanent. This board is the percentage of failure-exposed runs in which the agent retries, switches tool path or aborts correctly, under the standard tool-use prompt; higher is better.
Metric: Perturbation recovery rate (%): share of runs exposed to an injected failure in which the agent retries a transient fault, switches to an alternative tool path or aborts an unsolvable task, averaged over the four failure modes; 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 September 2028. 9 models tracked. Updated 30 Sep 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 37.31 | #52 |
| 2 | DeepSeek V4 Pro | 36.71 | #191 |
| 3 | Gemini 3.1 Pro (Preview) | 31.48 | #93 |
| 4 | GLM-5.1 | 30.43 | #186 |
| 5 | Qwen 3.5 397B A17B | 29.58 | #251 |
| 6 | Qwen 3.5 35B A3B | 29.48 | #486 |
| 7 | Qwen 3.6 27B | 28.75 | #344 |
| 8 | Claude Sonnet 4.6 | 24.88 | #165 |
| 9 | MiniMax-M2.7 | 23.34 | #523 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=toolmaze-perturbation-recovery-rate · How It Works · Data refreshed daily, snapshot 2026-11-16.