Algebraic Reasoning on AQuA (Performance %)
66.36Performance (%)ATOM
Evaluation Results
| Method | Links | |
|---|---|---|
| ATOMBackbone Model=Meta-Llama-3.1-8B-Instruct2026.05 | 66.36 | |
| LLM-DebateBackbone Model=Meta-Llama-3.1-8B-Instruct2026.05 | 65.89 | |
| RandomBackbone Model=Meta-Llama-3.1-8B-Instruct2026.05 | 65.42 | |
| AgentPruneBackbone Model=Meta-Llama-3.1-8B-Instruct2026.05 | 65.42 | |
| StarBackbone Model=Meta-Llama-3.1-8B-Instruct2026.05 | 64.95 | |
| G-DesignerBackbone Model=Meta-Llama-3.1-8B-Instruct2026.05 | 64.49 | |
| ARG-DesignerBackbone Model=Meta-Llama-3.1-8B-Instruct2026.05 | 63.55 | |
| ChainBackbone Model=Meta-Llama-3.1-8B-Instruct2026.05 | 62.15 | |
| CompleteBackbone Model=Meta-Llama-3.1-8B-Instruct2026.05 | 62.15 | |
| AgentDropoutBackbone Model=Meta-Llama-3.1-8B-Instruct2026.05 | 61.68 | |
| VanillaBackbone Model=Meta-Llama-3.1-8B-Instruct2026.05 | 57.01 | |
| CoTBackbone Model=Meta-Llama-3.1-8B-Instruct2026.05 | 54.21 |