Metric: Predictive-per ques. (higher is better)
| # | Model↕ | Predictive-per ques.▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | AI Core | 93.96 | No | Think before You Simulate: Symbolic Reasoning to... | 2025-06-12 | Code |
| 2 | redherring | 91.75 | No | - | - | - |
| 3 | VRDP | 91.35 | No | - | - | - |
| 4 | Fighttttt | 89.25 | No | - | - | - |
| 5 | neural | 87.48 | No | - | - | - |
| 6 | NERV | 87.28 | No | - | - | - |
| 7 | DCL | 82.03 | No | - | - | - |
| 8 | v0.1 | 72.6 | No | - | - | - |
| 9 | troublesolver | 72.38 | No | - | - | - |
| 10 | First_test | 68.7 | No | - | - | - |
| 11 | rnn_dyn | 68.61 | No | - | - | - |
| 12 | epoch 9 pgd_25_0.1_eps | 60.95 | No | - | - | - |
| 13 | TS_NS_IMPERIAL | 50.34 | No | - | - | - |