Enterprise Interface Task Completion on WorkArena++ L2
41.6Success RateGemini 3 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3 ProCategory=Proprietary, Teacher for A3-SYNTH=true2026.04 | 41.6 | |
| Gemini 3.1 Flash L.Category=Proprietary2026.04 | 21.1 | |
| Qwen3.5-27BCategory=Open-weight (base)2026.04 | 18.9 | |
| A3-Qwen3.5-9BCategory=A3 fine-tuned, Teacher=Gemini 3 Pro2026.04 | 9.7 | |
| A3-Qwen3.5-4BCategory=A3 fine-tuned, Teacher=Gemini 3 Pro2026.04 | 3.8 | |
| Qwen3.5-9BCategory=Open-weight (base)2026.04 | 2.2 | |
| Qwen3.5-4BCategory=Open-weight (base)2026.04 | 1.6 | |
| Qwen3.5-2BCategory=Open-weight (base)2026.04 | 0 | |
| A3-Qwen3.5-2BCategory=A3 fine-tuned, Teacher=Gemini 3 Pro2026.04 | 0 |