AsyncTool: leaderboard
Large language model (LLM)-based agents have shown strong capabilities in using external tools to solve complex tasks. However, existing evaluations often overlook the temporal dimension of tool use, especially the impact of tool response latency, and are usually limited to single-task settings. In real-world applications, multiple tasks often need to be executed concurrently, and overall efficien
Metric: Overall (self-reported). Source: benchmarklist.com. Saturation forecast: Around November 2026. 19 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 | 38.06 | #248 |
| 2 | Gemini 2.5 Pro | 32.44 | #152 |
| 3 | GPT-4o | 31.74 | #343 |
| 4 | GPT-5 | 31.32 | #98 |
| 5 | DeepSeek V3.1 Terminus | 28.93 | #220 |
| 6 | Qwen Max | 25.56 | #382 |
| 7 | Qwen 2.5 32B Instruct | 24.86 | #498 |
| 8 | Kimi K2 | 24.44 | #243 |
| 9 | Qwen 3 32B | 19.1 | #443 |
| 10 | Qwen 3 14B | 18.82 | #537 |
| 11 | GLM-4 32B | 15.17 | #459 |
| 12 | Qwen 3 8B | 10.67 | #674 |
| 13 | GLM-4 9B Chat | 6.88 | #916 |
| 14 | Llama 3.3 70B Instruct | 5.34 | #534 |
| 15 | Llama 3.1 8B Instruct | 1.26 | #1035 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=asynctool · How It Works · Data refreshed daily, snapshot 2026-10-20.