Metric: Counterfactual-per opt. (higher is better)
| # | Model↕ | Counterfactual-per opt.▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | AI Core | 96.61 | No | Think before You Simulate: Symbolic Reasoning to... | 2025-06-12 | Code |
| 2 | VRDP | 94.83 | No | - | - | - |
| 3 | redherring | 92.97 | No | - | - | - |
| 4 | neural | 91.42 | No | - | - | - |
| 5 | Fighttttt | 91.25 | No | - | - | - |
| 6 | NERV | 91.12 | No | - | - | - |
| 7 | rnn_dyn | 81.01 | No | - | - | - |
| 8 | DCL | 80.38 | No | - | - | - |
| 9 | troublesolver | 79.96 | No | - | - | - |
| 10 | v0.1 | 79.6 | No | - | - | - |
| 11 | TS_NS_IMPERIAL | 78.08 | No | - | - | - |
| 12 | First_test | 74.05 | No | - | - | - |
| 13 | epoch 9 pgd_25_0.1_eps | 66.65 | No | - | - | - |