ToolBench - Home Search — leaderboard
Metric: Task Score. Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 | 97 |
| 2 | text-davinci-003 | 97 |
| 3 | CodeLlama-34B-Python-hf | 91 |
| 4 | CodeLlama-34B-Instruct-hf | 90 |
| 5 | CodeLlama-34B-hf | 88 |
| 6 | CodeLlama-13B-hf | 87 |
| 7 | CodeLlama-13B-Python-hf | 86 |
| 8 | CodeLlama-13B-Instruct-hf | 85 |
| 9 | LLaMA-65B | 84 |
| 10 | CodeLlama-7B-Python-hf | 83 |
| 11 | Llama 2 70B | 83 |
| 12 | starcoder | 82 |
| 13 | GPT-3.5 Turbo | 80 |
| 14 | CodeLlama-7B-Instruct-hf | 78 |
| 15 | CodeLlama-7B-hf | 74 |
Interactive version: theaggregate.ai/benchmark?slug=toolbench-home-search · How the rankings work · Data refreshed daily, snapshot 2026-07-22.