ToolBench - Home Search — leaderboard

Metric: Task Score. Source: huggingface.co. 44 models tracked.

Top models

#ModelScore
1GPT-497
2text-davinci-00397
3CodeLlama-34B-Python-hf91
4CodeLlama-34B-Instruct-hf90
5CodeLlama-34B-hf88
6CodeLlama-13B-hf87
7CodeLlama-13B-Python-hf86
8CodeLlama-13B-Instruct-hf85
9LLaMA-65B84
10CodeLlama-7B-Python-hf83
11Llama 2 70B83
12starcoder82
13GPT-3.5 Turbo80
14CodeLlama-7B-Instruct-hf78
15CodeLlama-7B-hf74

Interactive version: theaggregate.ai/benchmark?slug=toolbench-home-search · How the rankings work · Data refreshed daily, snapshot 2026-07-22.