AI Compare

Toolathlon Benchmark Leaderboard

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.

Leaderboard

Top 19 models on Toolathlon Benchmark Leaderboard (scores from public evaluations).

  1. 1Gemini 3.5 Flash56.5% on Toolathlon Benchmark Leaderboard
  2. 2GPT-5.555.6% on Toolathlon Benchmark Leaderboard
  3. 3GPT-5.454.6% on Toolathlon Benchmark Leaderboard
  4. 4DeepSeek-V4-Pro-Max51.8% on Toolathlon Benchmark Leaderboard
  5. 5Kimi K2.650.0% on Toolathlon Benchmark Leaderboard
  6. 6Gemini 3 Flash49.4% on Toolathlon Benchmark Leaderboard
  7. 7DeepSeek-V4-Flash-Max47.8% on Toolathlon Benchmark Leaderboard
  8. 8GPT-5.246.3% on Toolathlon Benchmark Leaderboard
  9. 8MiniMax M2.746.3% on Toolathlon Benchmark Leaderboard
  10. 10MiniMax M2.143.5% on Toolathlon Benchmark Leaderboard
  11. 11GPT-5.4 mini42.9% on Toolathlon Benchmark Leaderboard
  12. 12GLM-5.140.7% on Toolathlon Benchmark Leaderboard
  13. 13Qwen3.6 Plus39.8% on Toolathlon Benchmark Leaderboard
  14. 14Qwen3.5-397B-A17B38.3% on Toolathlon Benchmark Leaderboard
  15. 15GPT-5.4 nano35.5% on Toolathlon Benchmark Leaderboard
  16. 16DeepSeek-V3.2-Speciale35.2% on Toolathlon Benchmark Leaderboard
  17. 16DeepSeek-V3.235.2% on Toolathlon Benchmark Leaderboard
  18. 16DeepSeek-V3.2 (Thinking)35.2% on Toolathlon Benchmark Leaderboard
  19. 19Qwen3.6-35B-A3B26.9% on Toolathlon Benchmark Leaderboard

Models tracked

Models with toolathlon in their evaluation profile.

  • No models linked yet.

View task leaderboards →