Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Exploration Focus on AnnoMI
Loading...
2.81
Exploration Focus
Base
2.3524
2.4712
2.59
2.7088
Feb 5, 2025
Exploration Focus
Updated 3mo ago
Evaluation Results
Method
Method
Links
Exploration Focus
Base
Backbone=Llama-3.1 70B
2025.02
2.81
COS
Backbone=Llama-3.1 70B
2025.02
2.77
CAMI-TE
Backbone=Llama-3.1 70B
2025.02
2.74
DIIR
Backbone=Llama-3.1 70B
2025.02
2.72
COS
Backbone=GPT-4o
2025.02
2.64
Base
Backbone=GPT-4o
2025.02
2.62
CAMI-TE
Backbone=GPT-4o
2025.02
2.6
DIIR
Backbone=GPT-4o
2025.02
2.59
CAMI
Backbone=Llama-3.1 70B
2025.02
2.44
CAMI
Backbone=GPT-4o
2025.02
2.37
Feedback
Search any
task
Search any
task