Character Relationship Network Updating on BookWorld FEN Existing scenario
82.7Win RateDeepSeek-V3.2-Think
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DeepSeek-V3.2-ThinkBaseline=vs. BookWorld (FEN)2026.04 | 82.7 | 3.73 | |
| Qwen3-32BBaseline=vs. BookWorld (FEN)2026.04 | 81.3 | 3.17 | |
| DeepSeek-V3.2Baseline=vs. BookWorld (FEN)2026.04 | 74.7 | 3.69 | |
| Gemini-2.5-ProBaseline=vs. BookWorld (FEN)2026.04 | 56 | 4.37 | |
| Llama3.3-70BBaseline=vs. BookWorld (FEN)2026.04 | 28 | 1.74 |