WebLINX
WebLINX: Measures browser, desktop, mobile, or GUI agents operating in interactive environments.
20rows
overallprimary metric
2026-05-05sampled
Metadata
Metrics
Overall, Intent, Element, Text
| Rank | Subject | Overall | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Llama-3-8B-Web | 28.88 | — | Imported | 2026-05-05 |
| 2 | Llama-2-13B | 25.21 | — | Imported | 2026-05-05 |
| 3 | S-LLaMA-2.7B | 25.02 | — | Imported | 2026-05-05 |
| 4 | Llama-2-7B | 24.57 | — | Imported | 2026-05-05 |
| 5 | Flan-T5-3B | 23.77 | — | Imported | 2026-05-05 |
| 6 | S-LLaMA-1.3B | 23.73 | — | Imported | 2026-05-05 |
| 7 | GPT-3.5F | 21.22 | — | Imported | 2026-05-05 |
| 8 | MindAct-3B | 20.94 | — | Imported | 2026-05-05 |
| 9 | Fuyu-8B | 19.97 | — | Imported | 2026-05-05 |
| 10 | Flan-T5-780M | 17.27 | — | Imported | 2026-05-05 |
| 11 | Pix2Act-1.3B | 16.88 | — | Imported | 2026-05-05 |
| 12 | MindAct-780M | 15.13 | — | Imported | 2026-05-05 |
| 13 | Flan-T5-250M | 14.99 | — | Imported | 2026-05-05 |
| 14 | MindAct-250M | 12.63 | — | Imported | 2026-05-05 |
| 15 | Pix2Act-282M | 12.51 | — | Imported | 2026-05-05 |
| 16 | GPT-4T | 10.72 | — | Imported | 2026-05-05 |
| 17 | GPT-4V | 10.45 | — | Imported | 2026-05-05 |
| 18 | GPT-3.5T | 8.51 | — | Imported | 2026-05-05 |
| 19 | Llama-2-13B | 5.16 | — | Imported | 2026-05-05 |
| 20 | Llama-2-7B | 4.04 | — | Imported | 2026-05-05 |
No matching rows.