List your company

Cross-lingual Alignment Correlation on m-MMLU (test)

0.9859Pearson CorrelationNASCA
0.6080680.7061590.804250.902341Jul 20, 2025

Evaluation results

MethodLinks
NASCABackbone=Mistral 0.3 7B, Aggregation Strategy=last2025.070.9859
MEXABackbone=Mistral 0.3 7B, Aggregation Strategy=average2025.070.9855
NASCABackbone=Qwen 2.5 7B, Aggregation Strategy=average2025.070.9849
NASCABackbone=Mistral 0.3 7B, Aggregation Strategy=average2025.070.9846
NAVCABackbone=Mistral 0.3 7B, Aggregation Strategy=average2025.070.9842
NASCABackbone=Qwen 2.5 7B, Aggregation Strategy=last2025.070.9792
NAVCABackbone=Llama 2 7B, Aggregation Strategy=last2025.070.979
NAVCABackbone=Llama 3.2 3B, Aggregation Strategy=average2025.070.9787
NAVCABackbone=Mistral 0.3 7B, Aggregation Strategy=last2025.070.9783
NAVCABackbone=Llama 2 7B, Aggregation Strategy=average2025.070.9762
NASCABackbone=Mistral 0.3 7B, Aggregation Strategy=weighted2025.070.9757
MEXABackbone=Llama 3.1 8B, Aggregation Strategy=average2025.070.972
NAVCABackbone=Llama 3.2 3B, Aggregation Strategy=last2025.070.9719
NASCABackbone=GLM 4 9B, Aggregation Strategy=average2025.070.9717
NASCABackbone=Llama 3.2 3B, Aggregation Strategy=weighted2025.070.9711
MEXABackbone=Llama 3.2 3B, Aggregation Strategy=weighted2025.070.9708
MEXABackbone=Qwen 2.5 7B, Aggregation Strategy=weighted2025.070.9705
NASCABackbone=Llama 3.1 8B, Aggregation Strategy=average2025.070.9704
NAVCABackbone=Llama 3.1 8B, Aggregation Strategy=average2025.070.9702
NAVCABackbone=Llama 3 8B, Aggregation Strategy=average2025.070.97
NASCABackbone=Llama 3.1 8B, Aggregation Strategy=weighted2025.070.97
MEXABackbone=Mistral 0.3 7B, Aggregation Strategy=weighted2025.070.9698
NASCABackbone=Llama 3.2 3B, Aggregation Strategy=last2025.070.9697
NASCABackbone=Qwen 2.5 7B, Aggregation Strategy=weighted2025.070.9696
NASCABackbone=Llama 3 8B, Aggregation Strategy=average2025.070.9693
NASCABackbone=Qwen 2.5 14B, Aggregation Strategy=average2025.070.9683
NAVCABackbone=Mistral 0.3 7B, Aggregation Strategy=weighted2025.070.9679
MEXABackbone=Llama 3 8B, Aggregation Strategy=average2025.070.9678
NASCABackbone=Llama 3.2 3B, Aggregation Strategy=average2025.070.9678
NASCABackbone=Llama 3.1 8B, Aggregation Strategy=last2025.070.9675
NAVCABackbone=GLM 4 9B, Aggregation Strategy=average2025.070.9673
NASCABackbone=Llama 3 8B, Aggregation Strategy=last2025.070.9669
NASCABackbone=Llama 3 8B, Aggregation Strategy=weighted2025.070.9663
NASCABackbone=GLM 4 9B, Aggregation Strategy=last2025.070.9661
NAVCABackbone=Llama 3.2 3B, Aggregation Strategy=weighted2025.070.9652
MEXABackbone=Llama 3.1 8B, Aggregation Strategy=weighted2025.070.9638
MEXABackbone=Llama 3 8B, Aggregation Strategy=weighted2025.070.9622
NAVCABackbone=Llama 3 8B, Aggregation Strategy=last2025.070.9612
NAVCABackbone=Llama 3.1 8B, Aggregation Strategy=last2025.070.9611
MEXABackbone=GLM 4 9B, Aggregation Strategy=weighted2025.070.9599
NASCABackbone=Qwen 2.5 14B, Aggregation Strategy=last2025.070.9597
NASCABackbone=GLM 4 9B, Aggregation Strategy=weighted2025.070.9578
NAVCABackbone=GLM 4 9B, Aggregation Strategy=last2025.070.9578
NASCABackbone=Llama 2 7B, Aggregation Strategy=last2025.070.9574
NAVCABackbone=Qwen 2.5 7B, Aggregation Strategy=weighted2025.070.9557
MEXABackbone=Llama 3.2 3B, Aggregation Strategy=average2025.070.9543
NASCABackbone=Llama 2 7B, Aggregation Strategy=average2025.070.9541
NAVCABackbone=Llama 3.1 8B, Aggregation Strategy=weighted2025.070.9504
NAVCABackbone=Qwen 2.5 7B, Aggregation Strategy=average2025.070.9499
NAVCABackbone=Llama 3 8B, Aggregation Strategy=weighted2025.070.9433
NAVCABackbone=Qwen 2.5 7B, Aggregation Strategy=last2025.070.9351
NAVCABackbone=Qwen 2.5 14B, Aggregation Strategy=average2025.070.9322
MEXABackbone=Llama 2 7B, Aggregation Strategy=weighted2025.070.93
NAVCABackbone=GLM 4 9B, Aggregation Strategy=weighted2025.070.9277
MEXABackbone=Llama 2 7B, Aggregation Strategy=average2025.070.9232
MEXABackbone=Qwen 2.5 14B, Aggregation Strategy=weighted2025.070.917
NAVCABackbone=Qwen 2.5 14B, Aggregation Strategy=last2025.070.917
NASCABackbone=Qwen 2.5 14B, Aggregation Strategy=weighted2025.070.9086
MEXABackbone=OLMO 2 7B, Aggregation Strategy=weighted2025.070.9076
NASCABackbone=OLMO 2 7B, Aggregation Strategy=weighted2025.070.9035
MEXABackbone=GLM 4 9B, Aggregation Strategy=average2025.070.8873
NASCABackbone=OLMO 2 7B, Aggregation Strategy=average2025.070.8871
MEXABackbone=Llama 2 7B, Aggregation Strategy=last2025.070.8861
NASCABackbone=OLMO 2 7B, Aggregation Strategy=last2025.070.886
NAVCABackbone=OLMO 2 7B, Aggregation Strategy=weighted2025.070.8802
MEXABackbone=OLMO 2 7B, Aggregation Strategy=average2025.070.8797
MEXABackbone=OLMO 2 7B, Aggregation Strategy=last2025.070.8772
NAVCABackbone=OLMO 2 7B, Aggregation Strategy=average2025.070.8663
MEXABackbone=Mistral 0.3 7B, Aggregation Strategy=last2025.070.8614
MEXABackbone=Qwen 2.5 7B, Aggregation Strategy=average2025.070.856
NAVCABackbone=Qwen 2.5 14B, Aggregation Strategy=weighted2025.070.8539
NAVCABackbone=OLMO 2 7B, Aggregation Strategy=last2025.070.8504
MEXABackbone=Llama 3 8B, Aggregation Strategy=last2025.070.8471
MEXABackbone=Llama 3.2 3B, Aggregation Strategy=last2025.070.8448
MEXABackbone=Llama 3.1 8B, Aggregation Strategy=last2025.070.8443
NASCABackbone=Llama 2 7B, Aggregation Strategy=weighted2025.070.8347
MEXABackbone=GLM 4 9B, Aggregation Strategy=last2025.070.8156
NAVCABackbone=Llama 2 7B, Aggregation Strategy=weighted2025.070.8086
MEXABackbone=Qwen 2.5 14B, Aggregation Strategy=average2025.070.7293
MEXABackbone=Qwen 2.5 7B, Aggregation Strategy=last2025.070.6312
MEXABackbone=Qwen 2.5 14B, Aggregation Strategy=last2025.070.6226