Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Language Modeling Accuracy on LLM Evaluation Benchmarks (Zero-shot)

68.8Llama-2 7B Accuracy

FP16

58.50461.17763.8566.523Dec 3, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
68.87472.474.67670.6
2025.12
67.673.672.475.173.369.3
2025.12
66.272.452.1---
2025.12
65.671.468.170.370.565.8
2025.12
63.567.76467.464.761.8
2025.12
63.260.666.8---
2025.12
62.864.567.467.871.367.8
2025.12
60.263.56364.467.864
2025.12
58.959.458.761.662.160.3