Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-ended generation on WritingPrompts (BERTScore, ROUGE-L)
Loading...
87.8
BERTScore
ReLAR
84.16
85.105
86.05
86.995
Jun 16, 2026
BERTScore
ROUGE-L
Updated 1mo ago
Evaluation Results
Method
Method
Links
BERTScore
ROUGE-L
ReLAR
2026.06
87.8
11.47
Mistral-7B-Instruct
2026.06
87.1
9.28
Llama-3-8B-Instruct
2026.06
86.9
8.74
Qwen2.5-7B
2026.06
86.4
7.94
Mistral-7B-v0.3
2026.06
85.8
6.83
Gemma-7B
2026.06
85.3
6.17
LLaMA-2-7B
2026.06
84.7
5.12
Falcon-7B
2026.06
84.3
4.63
Feedback
Search any
task
Search any
task