Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Poetry Revision on Arabic Dialectal Poetry Levant
Loading...
1.78
LLM-as-a-Judge Score
LLaMA-3-8B (Curriculum)
1.0416
1.2333
1.425
1.6167
Apr 30, 2026
LLM-as-a-Judge Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
LLM-as-a-Judge Score
LLaMA-3-8B (Curriculum)
Training Type=Curriculum
2026.04
1.78
LLaMA-3-8B (Random)
Training Type=Random
2026.04
1.74
ALLaM-7B-instruct (Curriculum)
Training Type=Curriculum
2026.04
1.67
ALLaM-7B-instruct (Random)
Training Type=Random
2026.04
1.66
Qwen-3-8B (Curriculum)
Training Type=Curriculum
2026.04
1.64
Qwen-3-8B (Random)
Training Type=Random
2026.04
1.63
Fanar-1-9B (Random)
Training Type=Random
2026.04
1.45
Fanar-1-9B (Curriculum)
Training Type=Curriculum
2026.04
1.36
Qwen-3-8B
Training Type=Base
2026.04
1.35
ALLaM-7B-instruct
Training Type=Instruct
2026.04
1.31
LLaMA-3-8B
Training Type=Base
2026.04
1.12
Fanar-1-9B
Training Type=Base
2026.04
1.07
Feedback
Search any
task
Search any
task