Proactive Demand Detection on IntentFlow No-Dem
92.8Business Metrics ScoreQwen3.5-Flash
Evaluation Results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Qwen3.5-Flash2026.04 | 92.8 | 94.1 | 93 | 92.7 | 91.3 | 95 | 96.3 | 92.2 | 94.3 | 89 | 93.1 | |
| Qwen3-30B-A3B2026.04 | 89.5 | 92.5 | 77.9 | 86.4 | 96.2 | 78.1 | 97 | 94.5 | 87.6 | 89 | 88.9 | |
| GPT-5-Mini2026.04 | 88.8 | 92.5 | 83.7 | 76.8 | 79.2 | 91.2 | 91.7 | 91.2 | 93.8 | 90.6 | 88 | |
| GPT-oss-120b2026.04 | 81.9 | 89.5 | 77.3 | 75 | 80.9 | 78.8 | 86.7 | 88.5 | 86.2 | 89.6 | 83.4 | |
| IntentFlow2026.04 | 81.9 | 88.3 | 88.4 | 80 | 86.9 | 90 | 86.7 | 84.8 | 87.1 | 78.3 | 85.2 | |
| Gemini-2.5-Flash-Lite2026.04 | 81.2 | 80.8 | 80.8 | 85 | 90.2 | 87.5 | 92.3 | 90.8 | 81.9 | 83.8 | 85.4 | |
| Claude-Haiku-4.52026.04 | 78 | 93.7 | 90.1 | 88.2 | 95.6 | 96.9 | 99.3 | 95.4 | 99 | 98.1 | 93.4 | |
| DeepSeek-V3.22026.04 | 76.2 | 90.4 | 90.7 | 85.5 | 100 | 96.9 | 97.3 | 88.5 | 88.1 | 95.5 | 90.9 | |
| Gemini-3-Flash2026.04 | 63.9 | 79.9 | 84.9 | 67.3 | 84.7 | 86.2 | 81.3 | 79.7 | 80.5 | 74.8 | 78.3 | |
| GPT-5-Nano2026.04 | 52.7 | 70.3 | 65.7 | 50.5 | 82.5 | 89.4 | 87.7 | 74.7 | 75.2 | 69.6 | 71.8 |