# Toolathlon

> Toolathlon spans 108 hand-crafted tasks averaging about 20 turns across 32 applications and 604 tools, and the best model reaches only 38.6% (Claude-4.5-Sonnet) with the best open-source model at 20.1%.

The Tool Decathlon: long-horizon tasks across 32 apps and 604 tools.

- **Category:** General capability
- **2026 frontier:** Best 38.6% (Claude-4.5-Sonnet); best open-source 20.1% (DeepSeek-V3.2-Exp)
- **Credibility:** Shows how far agents are from long-horizon work: 108 hand-crafted tasks averaging about 20 turns each, spanning 32 applications and 604 tools, and no system reaches 40%. The best open-source result is roughly half the best closed result, which is the widest such gap in this list.
- **Verification:** Verified
- **Source:** [Toolathlon (arXiv:2510.25726)](https://arxiv.org/abs/2510.25726)
- **Last updated:** 2026-10-04