Multi-Motif Counting on LLMTM Level 2 1.0 (test)
19.69AccuracyQwen2.5-32B
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2.5-32B2025.12 | 19.69 | |
| DeepSeek-R12025.12 | 13.41 | |
| GPT-4o-mini2025.12 | 13.07 | |
| DeepSeek-Qwen-14B2025.12 | 6.08 | |
| DeepSeek-Qwen-32B2025.12 | 5.4 | |
| DeepSeek-Qwen-7B2025.12 | 2 | |
| o32025.12 | 1.94 | |
| QwQ-32B2025.12 | 0.4 | |
| openPangu-7B2025.12 | 0.19 |