Web Task Execution on WebTailBench v1.5
79.6Process SuccessFaraGen1.5 Solver (GPT-5.4)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FaraGen1.5 Solver (GPT-5.4)Size=—2026.06 | 79.6 | 57.4 | |
| Fara1.5-27BSize=27B2026.06 | 72.9 | 40.2 | |
| o3 SoMSize=—2026.06 | 69.5 | 35 | |
| GPT-5 SoMSize=—2026.06 | 69.2 | 45.1 | |
| Fara1.5-9BSize=9B2026.06 | 64.5 | 32.3 | |
| Fara1.5-4BSize=4B2026.06 | 60.3 | 27.4 | |
| Fara-7BSize=7B2026.06 | 48.8 | 24.1 |