Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-document Question Answering on Chinese Multi-doc QA (test)
Loading...
44.8
Rouge-L
ChatGLM3-6B-32K
9.648
18.774
27.9
37.026
Nov 15, 2023
Rouge-L
Updated 4d ago
Evaluation Results
Method
Method
Links
Rouge-L
ChatGLM3-6B-32K
Context Window Size=32...
2023.11
44.8
Our model
Context Window Size=8K
2023.11
44.6
ChatGLM2-6B-32K
Context Window Size=32...
2023.11
37.6
Baichuan2-Turbo-192K
Context Window Size=192K
2023.11
36.8
GPT3.5-Turbo-16K
Context Window Size=16K
2023.11
28.7
Longchat-v1.5-7B-32K
Context Window Size=32...
2023.11
19.5
Vicuna-v1.5-7B-16K
Context Window Size=16...
2023.11
19.3
Qwen-14B-Chat
Context Window Size=8K...
2023.11
18.7
InternLM-7B-8K
Context Window Size=8K...
2023.11
16.3
Xgen-7B-8K
Context Window Size=8K...
2023.11
11
Feedback
Search any
task
Search any
task