Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Grammatical Error Correction on Falko-Merlin
Loading...
64.5
Precision
Llama-3.1-8B-Instruct
53.164
56.107
59.05
61.993
May 13, 2026
Precision
Recall
F0.5 Score
Updated 20d ago
Evaluation Results
Method
Method
Links
Precision
Recall
F0.5 Score
Llama-3.1-8B-Instruct
Decoding=edit-level ma...
2026.05
64.5
32.2
53.7
Qwen3-8B
Decoding=MBR
2026.05
62.5
38.2
55.5
Qwen3-8B
Decoding=Greedy
2026.05
61.5
39.9
55.5
gemma-3-12b-it
Decoding=MBR
2026.05
58.3
52.6
57
gemma-3-12b-it
Decoding=edit-level ma...
2026.05
57.6
39.6
52.8
gemma-3-12b-it
Decoding=Greedy
2026.05
57.2
53.9
56.5
Qwen3-8B
Decoding=edit-level ma...
2026.05
57.1
30.7
48.7
Llama-3.1-8B-Instruct
Decoding=Greedy
2026.05
55.2
51.3
54.4
Llama-3.1-8B-Instruct
Decoding=MBR
2026.05
53.6
50
52.8
Feedback
Search any
task
Search any
task