Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
End-to-End Task-Oriented Dialogue on MultiWOZ 2.2 (test)
Loading...
0.379
JGA
FNCTOD-LLAMA2-13B
0.15852
0.21576
0.273
0.33024
Feb 16, 2024
JGA
Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
JGA
Success Rate
FNCTOD-LLAMA2-13B
Protocol=Fine-tuned, B...
2024.02
0.379
0.444
VICUNA-13B-v1.5
Protocol=Zero-shot pro...
2024.02
0.338
0.231
BAICHUAN2-13B-CHAT
Protocol=Zero-shot pro...
2024.02
0.33
0.457
ZEPHYR-7B-BETA
Protocol=Zero-shot pro...
2024.02
0.323
0.575
VICUNA-7B-v1.5
Protocol=Zero-shot pro...
2024.02
0.294
0.377
ChatGPT
Protocol=Zero-shot pro...
2024.02
0.27
0.44
LLAMA2-13B-CHAT
Protocol=Zero-shot pro...
2024.02
0.258
0.277
LLAMA2-7B-CHAT
Protocol=Zero-shot pro...
2024.02
0.167
0.249
Feedback
Search any
task
Search any
task