Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Emotional Support Dialogue on SAGE
Loading...
72.1
Average Score
ESC-Skills
28.004
39.452
50.9
62.348
May 27, 2026
Average Score
Success Count
Failure Count
Updated 6d ago
Evaluation Results
Method
Method
Links
Average Score
Success Count
Failure Count
ESC-Skills
Backbone=Qwen3.6-Plus,...
2026.05
72.1
31
12
Qwen3.6-Plus
Backbone=Qwen3.6-Plus,...
2026.05
66.4
13
14
ESC-Skills
Backbone=Claude-Sonnet...
2026.05
63.6
11
21
ESC-Skills
Backbone=Claude-Opus-4...
2026.05
61.8
19
21
Claude-Opus-4.6
Backbone=Claude-Opus-4...
2026.05
61.2
16
18
Claude-Sonnet-4.6
Backbone=Claude-Sonnet...
2026.05
58.2
9
23
ESC-Skills
Backbone=Gemini-3.1-Fl...
2026.05
57.6
7
19
ESC-Skills
Backbone=GPT-5.4-0305-...
2026.05
57.4
7
19
GPT-5.4-0305-Global
Backbone=GPT-5.4-0305-...
2026.05
56.9
6
21
Gemini-3.1-Flash
Backbone=Gemini-3.1-Fl...
2026.05
56.2
4
21
ESC-Skills
Backbone=Claude-Haiku-...
2026.05
42.3
8
43
Claude-Haiku-4.5
Backbone=Claude-Haiku-...
2026.05
29.7
2
51
Feedback
Search any
task
Search any
task