| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MARS Overall (Evaluation Set) | Ours | Average Ranking (AI GPT-5)1.93 | 11 | 11d ago | |
| MARS Level 3 (Evaluation Set) | Ours | Avg Rank (AI GPT-5)1.9 | 11 | 11d ago | |
| MARS Level 2 (Evaluation Set) | Ours | Average Ranking (AI GPT-5)2.2 | 11 | 11d ago | |
| MARS Level 1 (test) | Ours | Average Ranking (AI GPT-5)1.7 | 11 | 11d ago |