ToolBench - WebShop Short — leaderboard
Metric: Task Score. Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | LLaMA-65B | 41.2 |
| 2 | Llama 2 13B | 31.67 |
| 3 | LLaMA-30B | 30.6 |
| 4 | Llama 2 70B | 30.45 |
| 5 | LLaMA-13B | 27.6 |
| 6 | CodeLlama-34B-Instruct-hf | 25.99 |
| 7 | CodeLlama-13B-Instruct-hf | 9.7 |
| 8 | Llama 2 7B | 6.92 |
| 9 | CodeLlama-34B-Python-hf | 6.47 |
| 10 | CodeLlama-34B-hf | 5.53 |
| 11 | pythia-1.4B | 5.2 |
| 12 | CodeLlama-13B-Python-hf | 2.4 |
| 13 | GPT-3.5 Turbo | 1.8 |
| 14 | CodeLlama-7B-Python-hf | 1.58 |
| 15 | GPT-NeoXT-Chat-Base-20B | 0.7 |
Interactive version: theaggregate.ai/benchmark?slug=toolbench-webshop-short · How the rankings work · Data refreshed daily, snapshot 2026-07-22.