Quantitative Mathematics on AIME
9.37AccuracyHILA
Evaluation Results
| Method | Links | |
|---|---|---|
| HILAType=MA, Backbone=LLaMA3-8B2026.03 | 9.37 | |
| G-SwarmType=MA, Backbone=LLaMA3-8B2026.03 | 5.78 | |
| DebateType=MA, Backbone=LLaMA3-8B2026.03 | 5.56 | |
| G-DebateType=MA, Backbone=LLaMA3-8B2026.03 | 5.19 | |
| A-PruneType=MA, Backbone=LLaMA3-8B2026.03 | 4.81 | |
| PHPType=MA, Backbone=LLaMA3-8B2026.03 | 4.44 | |
| AFlowType=MA, Backbone=LLaMA3-8B2026.03 | 4.44 | |
| SCType=SA, Backbone=LLaMA3-8B2026.03 | 4.07 | |
| CoTType=SA, Backbone=LLaMA3-8B2026.03 | 3.7 | |
| DyLANType=MA, Backbone=LLaMA3-8B2026.03 | 3.7 | |
| VanillaType=SA, Backbone=LLaMA3-8B2026.03 | 2.96 |