all the models — AI benchmark observatory
← Benchmarks

Toolathlon

Tool Decathlon is a comprehensive benchmark for evaluating AI agents' ability to use multiple tools across diverse task categories. It measures proficiency in tool selection, sequencing, and execution across ten different tool-use scenarios.

id toolathlon · max 1 · 42 models reported

#ModelScore
1GLM-5.3-Flash
Zhipu AI · open
0.78
2Muse Spark 1.1
Meta
0.76
3DeepSeek-V4-Pro-0813
DeepSeek · open
0.74
4Hy4 preview
Tencent · open
0.74
5Qwen3.8 Flash
Alibaba Cloud / Qwen Team
0.73
6Qwen3.8-Flash-Next
Alibaba Cloud / Qwen Team · open
0.73
7Kimi K3
Moonshot AI · open
0.73
8GLM-5.3
Zhipu AI · open
0.73
9Qwen3.8 Max
Alibaba Cloud / Qwen Team · open
0.72
10DeepSeek-V4-Flash-0731
DeepSeek · open
0.70