Personalized Assistant Interaction on LifeSim-Eval Single-Scenario
80.6Explicit Intent RecognitionDeepSeek-V3.2 Thinking
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek-V3.2 ThinkingAccess Type=Open-source2026.03 | 80.6 | 59.3 | 75.8 | 58.2 | 84.1 | 92.1 | 63.4 | 74 | |
| GPT-5Access Type=Close-source2026.03 | 79.5 | 52.2 | 76.9 | 48.9 | 83.9 | 97.5 | 60.3 | 74.6 | |
| GPT-4oAccess Type=Close-source2026.03 | 79 | 52.6 | 72.1 | 48.1 | 81.4 | 90 | 60.5 | 74.1 | |
| DeepSeek-V3.2Access Type=Open-source2026.03 | 78.6 | 54.6 | 73.5 | 50.8 | 85.2 | 91.5 | 65 | 75.5 | |
| Qwen3 14BAccess Type=Open-source2026.03 | 77 | 46.3 | 68.3 | 41.3 | 79.1 | 86.8 | 61.8 | 74.7 | |
| gpt-oss 20BAccess Type=Open-source2026.03 | 76.9 | 43.7 | 72.6 | 41.1 | 83.4 | 91 | 57.1 | 75.2 | |
| Qwen3 32BAccess Type=Open-source2026.03 | 76.6 | 51.2 | 70.3 | 47.4 | 83.9 | 89.9 | 61.7 | 75.8 | |
| gpt-oss 120BAccess Type=Open-source2026.03 | 76.4 | 44.3 | 73.3 | 42.6 | 85.8 | 93 | 59.8 | 74.2 | |
| Claude-Sonnet-4.5Access Type=Close-source2026.03 | 76.1 | 49.2 | 73 | 46.5 | 89.8 | 96.9 | 60.9 | 75.5 | |
| Qwen3 8BAccess Type=Open-source2026.03 | 75.7 | 44.4 | 64.4 | 38.4 | 75 | 83.3 | 60.5 | 73.5 | |
| Gemma3-it 27BAccess Type=Open-source2026.03 | 72.7 | 44.2 | 65.4 | 39.3 | 78.4 | 81.3 | 61.8 | 75.6 | |
| Llama3.1-it 70BAccess Type=Open-source2026.03 | 71.7 | 41.4 | 60.9 | 35.5 | 79.6 | 84.8 | 60.4 | 73.5 | |
| Llama3.1-it 8BAccess Type=Open-source2026.03 | 70.3 | 40.3 | 58.4 | 33.8 | 69.3 | 72.8 | 58.5 | 73.8 | |
| Gemma3-it 12BAccess Type=Open-source2026.03 | 67.8 | 35.8 | 57 | 30 | 67.3 | 71 | 60.7 | 73.5 |