ToolBench - Trip Booking — leaderboard
Metric: Task Score. Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 | 96.7 |
| 2 | text-davinci-003 | 89.2 |
| 3 | CodeLlama-34B-Instruct-hf | 89.17 |
| 4 | CodeLlama-34B-hf | 88.33 |
| 5 | CodeLlama-34B-Python-hf | 85.83 |
| 6 | GPT-3.5 Turbo | 85.8 |
| 7 | CodeLlama-13B-Instruct-hf | 72.5 |
| 8 | Llama 2 70B | 71.67 |
| 9 | CodeLlama-13B-hf | 70.83 |
| 10 | CodeLlama-7B-Python-hf | 68.33 |
| 11 | LLaMA-65B | 65.8 |
| 12 | CodeLlama-7B-hf | 63.33 |
| 13 | CodeLlama-13B-Python-hf | 62.5 |
| 14 | CodeLlama-7B-Instruct-hf | 61.67 |
| 15 | Llama 2 13B | 53.33 |
Interactive version: theaggregate.ai/benchmark?slug=toolbench-trip-booking · How the rankings work · Data refreshed daily, snapshot 2026-07-22.