Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

General LLM Evaluation on AlignBench

7.27Reasoning Score

Qwen2.5-14B

3.74444.65975.5756.4903Jun 30, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.06
7.277.087.17
2025.06
6.596.666.62
2025.06
6.526.526.52
2025.06
6.036.186.11
2025.06
5.576.065.81
2025.06
5.256.015.63
2025.06
5.195.95.55
2025.06
5.155.825.49
2025.06
4.95.515.2
2025.06
4.95.655.28
2025.06
4.795.625.21
2025.06
4.725.615.16
2025.06
4.655.55.08
2025.06
4.535.394.96
2025.06
4.465.524.99
2025.06
4.375.344.85
2025.06
4.25.244.72
2025.06
4.15.54.8
2025.06
4.025.234.63
2025.06
3.885.044.46