Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Machine Translation Evaluation on WMT MQM System-level 22
Loading...
91.2
Overall Score
EAPrompt
68.84
74.645
80.45
86.255
Mar 24, 2023
Overall Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Overall Score
EAPrompt
Backbone=GPT-3.5-Turbo...
2023.03
91.2
EAPrompt
Backbone=GPT-3.5-Turbo...
2023.03
89.4
GEMBA
Backbone=GPT-3.5-Turbo...
2023.03
86.9
GEMBA
Backbone=GPT-3.5-Turbo...
2023.03
86.5
EAPrompt
Backbone=Llama2-70b-Ch...
2023.03
85.8
EAPrompt
Backbone=Llama2-70b-Ch...
2023.03
85.4
MetricsX-XXL
Reference provided=true
2023.03
85
BLEURT20
Reference provided=true
2023.03
84.7
EAPrompt
Backbone=Mixtral-8x7b-...
2023.03
84
COMET22
Reference provided=true
2023.03
83.9
UniTE
Reference provided=true
2023.03
82.8
EAPrompt
Backbone=Mixtral-8x7b-...
2023.03
82.5
COMET-QE
Reference provided=false
2023.03
78.1
UniTE-src
Reference provided=false
2023.03
75.9
MaTESe-QE
Reference provided=false
2023.03
74.8
GEMBA
Backbone=Llama2-70b-Ch...
2023.03
74.1
GEMBA
Backbone=Mixtral-8x7b-...
2023.03
74.1
GEMBA
Backbone=Llama2-70b-Ch...
2023.03
72.6
GEMBA
Backbone=Mixtral-8x7b-...
2023.03
69.7
Feedback
Search any
task
Search any
task