ToolBench - WebShop Long — leaderboard
Metric: Task Score. Source: huggingface.co. 44 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | starcoder | 2.6 |
| 2 | Llama 2 70B | 1.53 |
| 3 | Llama 2 13B | 0.6 |
| 4 | GPT-3.5 Turbo | 0 |
| 5 | GPT-4 | 0 |
| 6 | LLaMA-65B | 0 |
| 7 | LLaMA-13B | 0 |
| 8 | pythia-12B | 0 |
| 9 | LLaMA-30B | 0 |
| 10 | Llama 2 7B | 0 |
| 11 | Dolly V2 12B | 0 |
| 12 | CodeLlama-34B-Instruct-hf | 0 |
| 13 | opt-1.3B | 0 |
| 14 | opt-30B | 0 |
| 15 | StableLM Tuned Alpha 7B | 0 |
Interactive version: theaggregate.ai/benchmark?slug=toolbench-webshop-long · How the rankings work · Data refreshed daily, snapshot 2026-07-22.