Reasoning on GeoQuery
84.64AccuracyBGE-KMeans
Evaluation results
| Method | Links | |
|---|---|---|
| BGE-KMeansModel=Llama3-70B, Shots=1282025.06 | 84.64 | |
| CLGModel=Llama3-70B, Shots=1282025.06 | 84.64 | |
| Best-of-NModel=Llama3-70B, Shots=1282025.06 | 80.71 | |
| EPR-KMeansModel=Llama3-70B, Shots=1282025.06 | 78.21 | |
| RandomModel=Llama3-70B, Shots=1282025.06 | 73.36 | |
| EPR-KMeansModel=Qwen2.5-72B, Shots=1282025.06 | 62.86 | |
| CLGModel=Qwen2.5-72B, Shots=1282025.06 | 62.5 | |
| Latent-BayesianModel=Llama3-70B, Shots=1282025.06 | 62.14 | |
| BGE-KMeansModel=Qwen2.5-72B, Shots=1282025.06 | 61.79 | |
| Best-of-NModel=Qwen2.5-72B, Shots=1282025.06 | 61.07 | |
| RandomModel=Qwen2.5-72B, Shots=1282025.06 | 57.29 | |
| BM25-MajorModel=Qwen2.5-72B, Shots=1282025.06 | 52.5 | |
| BM25-MajorModel=Llama3-70B, Shots=1282025.06 | 43.21 | |
| Latent-BayesianModel=Qwen2.5-72B, Shots=1282025.06 | 27.5 |