Cross-lingual Alignment Correlation on m-ARC FLORES (test)
0.9867Pearson CorrelationNAVCA
Evaluation Results
| Method | Links | |
|---|---|---|
| NAVCABackbone=Mistral 0.3 7B, Aggregation Strategy=last2025.07 | 0.9867 | |
| NAVCABackbone=Mistral 0.3 7B, Aggregation Strategy=average2025.07 | 0.9847 | |
| NAVCABackbone=Qwen 2.5 7B, Aggregation Strategy=average2025.07 | 0.982 | |
| NAVCABackbone=Qwen 2.5 7B, Aggregation Strategy=last2025.07 | 0.9804 | |
| NAVCABackbone=Qwen 2.5 14B, Aggregation Strategy=average2025.07 | 0.9786 | |
| MEXABackbone=Qwen 2.5 14B, Aggregation Strategy=weighted2025.07 | 0.9773 | |
| NAVCABackbone=Llama 3.1 8B, Aggregation Strategy=average2025.07 | 0.9756 | |
| NAVCABackbone=Qwen 2.5 14B, Aggregation Strategy=last2025.07 | 0.9756 | |
| NAVCABackbone=Llama 3.1 8B, Aggregation Strategy=last2025.07 | 0.9751 | |
| NAVCABackbone=GLM 4 9B, Aggregation Strategy=average2025.07 | 0.9731 | |
| NAVCABackbone=Llama 3 8B, Aggregation Strategy=last2025.07 | 0.9728 | |
| NAVCABackbone=GLM 4 9B, Aggregation Strategy=last2025.07 | 0.9727 | |
| NAVCABackbone=Llama 3 8B, Aggregation Strategy=average2025.07 | 0.9725 | |
| NASCABackbone=GLM 4 9B, Aggregation Strategy=average2025.07 | 0.9713 | |
| NASCABackbone=GLM 4 9B, Aggregation Strategy=last2025.07 | 0.9705 | |
| NASCABackbone=Qwen 2.5 14B, Aggregation Strategy=average2025.07 | 0.9696 | |
| NASCABackbone=Qwen 2.5 14B, Aggregation Strategy=weighted2025.07 | 0.9692 | |
| NAVCABackbone=Qwen 2.5 7B, Aggregation Strategy=weighted2025.07 | 0.9692 | |
| MEXABackbone=GLM 4 9B, Aggregation Strategy=weighted2025.07 | 0.9688 | |
| NASCABackbone=Qwen 2.5 14B, Aggregation Strategy=last2025.07 | 0.9687 | |
| NAVCABackbone=Qwen 2.5 14B, Aggregation Strategy=weighted2025.07 | 0.9686 | |
| NAVCABackbone=Llama 2 7B, Aggregation Strategy=last2025.07 | 0.9682 | |
| NAVCABackbone=Llama 3.1 8B, Aggregation Strategy=weighted2025.07 | 0.9678 | |
| MEXABackbone=Qwen 2.5 7B, Aggregation Strategy=weighted2025.07 | 0.9664 | |
| MEXABackbone=Llama 3.1 8B, Aggregation Strategy=weighted2025.07 | 0.9657 | |
| NASCABackbone=Llama 3.1 8B, Aggregation Strategy=weighted2025.07 | 0.965 | |
| NAVCABackbone=Llama 2 7B, Aggregation Strategy=average2025.07 | 0.9649 | |
| NAVCABackbone=GLM 4 9B, Aggregation Strategy=weighted2025.07 | 0.9638 | |
| MEXABackbone=Llama 3 8B, Aggregation Strategy=weighted2025.07 | 0.9624 | |
| NAVCABackbone=OLMO 2 7B, Aggregation Strategy=last2025.07 | 0.9624 | |
| NAVCABackbone=Llama 3 8B, Aggregation Strategy=weighted2025.07 | 0.9616 | |
| NASCABackbone=GLM 4 9B, Aggregation Strategy=weighted2025.07 | 0.9592 | |
| NASCABackbone=Llama 3.1 8B, Aggregation Strategy=last2025.07 | 0.9591 | |
| MEXABackbone=Qwen 2.5 7B, Aggregation Strategy=average2025.07 | 0.9589 | |
| MEXABackbone=Mistral 0.3 7B, Aggregation Strategy=average2025.07 | 0.9575 | |
| NASCABackbone=Llama 3 8B, Aggregation Strategy=weighted2025.07 | 0.9575 | |
| NASCABackbone=Llama 3.1 8B, Aggregation Strategy=average2025.07 | 0.957 | |
| NAVCABackbone=OLMO 2 7B, Aggregation Strategy=average2025.07 | 0.9569 | |
| NASCABackbone=Mistral 0.3 7B, Aggregation Strategy=last2025.07 | 0.9565 | |
| MEXABackbone=Llama 3.1 8B, Aggregation Strategy=average2025.07 | 0.9551 | |
| NAVCABackbone=Llama 3.2 3B, Aggregation Strategy=last2025.07 | 0.9545 | |
| NAVCABackbone=Mistral 0.3 7B, Aggregation Strategy=weighted2025.07 | 0.954 | |
| NASCABackbone=Mistral 0.3 7B, Aggregation Strategy=average2025.07 | 0.9539 | |
| NASCABackbone=Llama 3 8B, Aggregation Strategy=last2025.07 | 0.9535 | |
| NASCABackbone=Llama 3 8B, Aggregation Strategy=average2025.07 | 0.9522 | |
| NAVCABackbone=Llama 3.2 3B, Aggregation Strategy=average2025.07 | 0.9522 | |
| NASCABackbone=Qwen 2.5 7B, Aggregation Strategy=last2025.07 | 0.951 | |
| NASCABackbone=Qwen 2.5 7B, Aggregation Strategy=average2025.07 | 0.9479 | |
| NASCABackbone=Mistral 0.3 7B, Aggregation Strategy=weighted2025.07 | 0.947 | |
| MEXABackbone=Llama 3 8B, Aggregation Strategy=average2025.07 | 0.9464 | |
| NASCABackbone=Qwen 2.5 7B, Aggregation Strategy=weighted2025.07 | 0.9438 | |
| MEXABackbone=Llama 2 7B, Aggregation Strategy=weighted2025.07 | 0.9426 | |
| NAVCABackbone=Llama 3.2 3B, Aggregation Strategy=weighted2025.07 | 0.9412 | |
| NASCABackbone=Llama 2 7B, Aggregation Strategy=last2025.07 | 0.94 | |
| NASCABackbone=Llama 2 7B, Aggregation Strategy=average2025.07 | 0.9369 | |
| MEXABackbone=Llama 3.2 3B, Aggregation Strategy=weighted2025.07 | 0.9319 | |
| MEXABackbone=Mistral 0.3 7B, Aggregation Strategy=weighted2025.07 | 0.931 | |
| NASCABackbone=Llama 3.2 3B, Aggregation Strategy=weighted2025.07 | 0.9308 | |
| MEXABackbone=Mistral 0.3 7B, Aggregation Strategy=last2025.07 | 0.9279 | |
| NASCABackbone=Llama 2 7B, Aggregation Strategy=weighted2025.07 | 0.9277 | |
| NASCABackbone=OLMO 2 7B, Aggregation Strategy=last2025.07 | 0.9261 | |
| NAVCABackbone=Llama 2 7B, Aggregation Strategy=weighted2025.07 | 0.9241 | |
| MEXABackbone=GLM 4 9B, Aggregation Strategy=average2025.07 | 0.9225 | |
| NASCABackbone=Llama 3.2 3B, Aggregation Strategy=last2025.07 | 0.9212 | |
| MEXABackbone=OLMO 2 7B, Aggregation Strategy=last2025.07 | 0.9187 | |
| NASCABackbone=Llama 3.2 3B, Aggregation Strategy=average2025.07 | 0.9186 | |
| NASCABackbone=OLMO 2 7B, Aggregation Strategy=average2025.07 | 0.9177 | |
| MEXABackbone=Llama 3.2 3B, Aggregation Strategy=average2025.07 | 0.9142 | |
| NAVCABackbone=OLMO 2 7B, Aggregation Strategy=weighted2025.07 | 0.9133 | |
| MEXABackbone=Llama 2 7B, Aggregation Strategy=average2025.07 | 0.9124 | |
| MEXABackbone=Llama 3 8B, Aggregation Strategy=last2025.07 | 0.8979 | |
| MEXABackbone=OLMO 2 7B, Aggregation Strategy=average2025.07 | 0.8925 | |
| MEXABackbone=Llama 3.2 3B, Aggregation Strategy=last2025.07 | 0.8925 | |
| NASCABackbone=OLMO 2 7B, Aggregation Strategy=weighted2025.07 | 0.8853 | |
| MEXABackbone=Llama 2 7B, Aggregation Strategy=last2025.07 | 0.8853 | |
| MEXABackbone=Llama 3.1 8B, Aggregation Strategy=last2025.07 | 0.8833 | |
| MEXABackbone=OLMO 2 7B, Aggregation Strategy=weighted2025.07 | 0.88 | |
| MEXABackbone=Qwen 2.5 14B, Aggregation Strategy=average2025.07 | 0.8709 | |
| MEXABackbone=GLM 4 9B, Aggregation Strategy=last2025.07 | 0.8543 | |
| MEXABackbone=Qwen 2.5 7B, Aggregation Strategy=last2025.07 | 0.7938 | |
| MEXABackbone=Qwen 2.5 14B, Aggregation Strategy=last2025.07 | 0.7729 |