AIME 2024 aime-2024 Leaderboard
Auto-discovered from papers reporting AIME 2024 (Accuracy). Β· Metric: Accuracy (higher is better) Β· π’ Updated 2h ago
| # | Model | Accuracy | Paper |
|---|---|---|---|
| 1 | PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning | 90.90 | link |
| 2 | + GRPO-Ξ» | 74.40 | link |
| 3 | Vanilla | 74.10 | link |
| 4 | +GRPO | 72.70 | link |
| 5 | +LP | 71.90 | link |
| 6 | Weak-to-Strong Generalization via Direct On-Policy Distillation | 58.30 | link |