New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Tool-Decathlon benchmark
AI model leaderboard for the Tool-Decathlon benchmark. Compare how large language models score on Tool-Decathlon, see the full ranking, and understand what this AI benchmark measures. Claude Sonnet 4.5 currently leads with 38.6. Ten-task agentic suite probing varied tool-use patterns: search, code, calculation, scheduling, etc.
Leaderboard
| # | Model | Organization | Score | Variant | Source |
|---|---|---|---|---|---|
| #1 | Claude Sonnet 4.5 | Anthropic | 38.6 | cited-deepseek-v3-2 | official ↗ |
| #2 | Gemini 3 Pro | Google DeepMind | 36.4 | cited-deepseek-v3-2 | official ↗ |
| #3 | DeepSeek-V3.2 | DeepSeek | 35.2 | thinking | official ↗ |
| #4 | GPT-5 | OpenAI | 29 | cited-deepseek-v3-2 | official ↗ |
| #5 | Kimi K2 Thinking | Moonshot | 17.6 | thinking-cited-deepseek-v3-2 | official ↗ |
| #6 | MiniMax-M2 | MiniMax | 16 | cited-deepseek-v3-2 | official ↗ |
Frequently asked questions about Tool-Decathlon
What is the Tool-Decathlon benchmark?
Ten-task agentic suite probing varied tool-use patterns: search, code, calculation, scheduling, etc.
How is the Tool-Decathlon benchmark scored?
Tool-Decathlon is scored using the accuracy metric, where a higher score is better. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on Tool-Decathlon?
As of the latest reported scores on GenAIList, Claude Sonnet 4.5 achieves the highest result on Tool-Decathlon with a score of 38.6.
Is a higher Tool-Decathlon score better?
Yes. On Tool-Decathlon a higher score indicates better performance, so models near the top of the leaderboard are the strongest.