When2Tool (Multi-Hop): leaderboard

Metric: Accuracy (%; exact-form answers in a boxed final response, checked by a deterministic evaluator; simulated offline tool environments at easy, medium and hard difficulty; 450 multi-hop test tasks in 3 environments, each a chain of three dependent tool calls; tools offered under the neutral default prompt; mean of three seeds). Source: arxiv.org. Saturation forecast: Estimated already saturated. 6 models tracked.

Top models

#ModelScore
1Qwen 3 32B88.9
2Qwen 3 14B87.5
3Qwen 3 4B 2507 Instruct82.1
4Llama 3.3 70B Instruct62.4
5Llama 3.1 8B40.2
6Qwen 3 1.7B21.2

Interactive version: theaggregate.ai/benchmark?slug=when2tool-multi-hop · How It Works · Data refreshed daily, snapshot 2026-09-26.