ToolBench - The Cat API — leaderboard

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

Top models

#ModelScore
1text-davinci-00398
2GPT-496
3CodeLlama-7B-Instruct-hf94
4CodeLlama-13B-Python-hf92.35
5GPT-3.5 Turbo92
6CodeLlama-7B-hf92
7CodeLlama-13B-Instruct-hf89.58
8CodeLlama-34B-Python-hf88.42
9CodeLlama-7B-Python-hf88
10CodeLlama-13B-hf86.83
11CodeLlama-34B-Instruct-hf86
12CodeLlama-34B-hf85
13Llama 2 70B84.39
14LLaMA-30B84
15starcoder84

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