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

Counseling Dialogue Evaluation on XInsight-Bench CBT

4.5CTS-R #1

Qwen3

1.77522.48263.193.8974Jan 21, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.01
4.54.434.984.765.025.244.924.914.794.794.724.957.96
2026.01
4.44.254.754.554.754.624.624.454.454.44.354.4554.04
2026.01
4.244.14.664.454.6654.764.834.664.344.214.6254.53
2026.01
4.194.414.884.164.884.184.764.714.654.884.534.8255.05
2026.01
3.413.053.933.383.933.863.723.343.483.022.973.3441.43
2026.01
3.342.954.013.354.274.543.894.23.872.522.963.5543.45
2026.01
3.252.753.53.23.84.053.33.253.252.652.653.238.85
2026.01
1.881.532.1222.413.062.181.942.061.181.241.7123.31