Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-turn conversation on MT-Eval
Loading...
8.28
Accuracy
Rhea
4.016
5.123
6.23
7.337
Dec 7, 2025
Accuracy
Latency
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Latency
Rhea
2025.12
8.28
14.42
Reply-Soft-Compress
2025.12
7.83
15.21
BM25(RAG)
2025.12
7.82
8.49
Vanilla
2025.12
7.77
11.41
Recent-k
2025.12
7.76
8.79
Summary
2025.12
6.83
17.26
Memocha
Base Model=Vicuna-7B
2025.12
6.4
4.8
LongAlpaca
Base Model=Vicuna-7B
2025.12
5.89
5.44
LlmLingua2
2025.12
4.18
13.3
Feedback
Search any
task
Search any
task