Enterprise Interface Task Completion on WorkArena++ L2
41.6Success Rate
Gemini 3 Pro
Updated 9d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.04 | 41.6 | |
2026.04 | 21.1 | |
2026.04 | 18.9 | |
2026.04 | 9.7 | |
2026.04 | 3.8 | |
2026.04 | 2.2 | |
2026.04 | 1.6 | |
2026.04 | 0 | |
2026.04 | 0 |
Gemini 3 Pro
| Method | Links | |
|---|---|---|
2026.04 | 41.6 | |
2026.04 | 21.1 | |
2026.04 | 18.9 | |
2026.04 | 9.7 | |
2026.04 | 3.8 | |
2026.04 | 2.2 | |
2026.04 | 1.6 | |
2026.04 | 0 | |
2026.04 | 0 |