Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Dialogue Response Generation on KEEM memories 1.0 (test)
Loading...
4.56
Perplexity
Llama10.8B tuned Korean
4.4184
5.3742
6.33
7.2858
Jan 9, 2026
Perplexity
Voting Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Perplexity
Voting Score
Llama10.8B tuned Korean
parameters=10.8B, tuni...
2026.01
4.56
74
Phi2.8B tuned Korean
parameters=2.8B, tunin...
2026.01
4.61
79
Llama2 13B
parameters=13B
2026.01
6.89
82
Llama2 7B
parameters=7B
2026.01
6.99
81
FiD
2026.01
7.88
68
FiD-RAG
2026.01
7.9
77
RAG
2026.01
8.1
67
Feedback
Search any
task
Search any
task