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

Code Reasoning on CUE-Bench

1.2VT Score

Qwen2.5-0.5B

-0.0480.2760.60.924Jun 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
1.21610.515.68.19.410.1
2026.06
0.916.310.416.27.7910.1
2026.06
0.712.76.513.34.25.47.2
2026.06
0.711.26.312.15.35.36.8
2026.06
0.575.111.24.44.25.4
2026.06
0.58.149.83.33.74.9
2026.06
0.58.3410.73.55.25.3
2026.06
0.55.72.68.33.13.53.9
2026.06
0.48.54.17.93.63.54.7
2026.06
0.42.21.93.30.40.41.4
2026.06
0.29.87.211.64.13.76.1
2026.06
0.14.22.35.21.91.42.5
2026.06
0.15.42.372.21.93.2
2026.06
0.14.32.55.91.61.62.7
2026.06
05.72.38.62.83.23.8
2026.06
04.60001.91.1