Metric: Explanatory-per ques. (higher is better)
| # | Model↕ | Explanatory-per ques.▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | AI Core | 99.81 | No | Think before You Simulate: Symbolic Reasoning to... | 2025-06-12 | Code |
| 2 | redherring | 96.98 | No | - | - | - |
| 3 | neural | 95.99 | No | - | - | - |
| 4 | Fighttttt | 95.46 | No | - | - | - |
| 5 | NERV | 94.98 | No | - | - | - |
| 6 | TS_NS_IMPERIAL | 91.98 | No | - | - | - |
| 7 | VRDP | 91.94 | No | - | - | - |
| 8 | DCL | 82.82 | No | - | - | - |
| 9 | troublesolver | 81.56 | No | - | - | - |
| 10 | v0.1 | 81.24 | No | - | - | - |
| 11 | First_test | 79.6 | No | - | - | - |
| 12 | rnn_dyn | 75.62 | No | - | - | - |
| 13 | epoch 9 pgd_25_0.1_eps | 72.78 | No | - | - | - |