Toolathlon Verified average assistant turns
Average assistant turns per Toolathlon Verified trajectory.
4 models
Lower is better on this benchmark.
- 1Claude Opus 5Anthropic23.5
- 2Claude Fable 5.1Anthropic23.7
- 3Claude Opus 5.5Anthropic26.9
- 4Claude Sonnet 5.5Anthropic31.6
About this benchmark
- Metric
- Average trajectory length
- Tasks
- 108 verified real-world tool-use tasks
- Authors
- Anthropic (2026)
Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.