Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Empathetic Dialogue on ICLR
Loading...
96.7
Success Rate (SR)
gemini-2.5-flash
77.356
82.378
87.4
92.422
Mar 17, 2026
Success Rate (SR)
Average Turn Length/Time (AT)
Empathy Score (ES)
Empathy Appropriateness (EA)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate (SR)
Average Turn Length/Time (AT)
Empathy Score (ES)
Empathy Appropriateness (EA)
gemini-2.5-flash
Type=Proprietary LLM API
2026.03
96.7
1.73
3.83
3.98
EmoLLM
Type=open-weight model
2026.03
96.2
1.21
4.21
3.95
gpt-5-mini
Type=Proprietary LLM API
2026.03
92.1
2.08
3.91
3.57
gemini-3.1-flash-lite
Type=Proprietary LLM API
2026.03
83.1
1.32
3.88
3.49
gpt-5-nano
Type=Proprietary LLM API
2026.03
78.1
2.61
4.08
3.02
Feedback
Search any
task
Search any
task