Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-Context Language Understanding on Long tasks 4 tasks (val)
Loading...
83.24
Long Tasks Score
EuroBERT/EuroBERT-610m
74.0672
76.4486
78.83
81.2114
Mar 12, 2026
Long Tasks Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Long Tasks Score
EuroBERT/EuroBERT-610m
Size=608M
2026.03
83.24
polish-roberta-8k
Size=443M
2026.03
83.16
sdadas/polish-roberta-large-v2
Size=435M
2026.03
82.18
jhu-clsp/mmBERT-base
Size=307M
2026.03
82.08
polish-roberta-8k-12L
Size=291M
2026.03
81.86
allegro/herbert-large-cased
Size=355M
2026.03
81.67
polish-roberta-8k-6L (simple)
Size=216M
2026.03
81.16
FacebookAI/xlm-roberta-large
Size=560M
2026.03
81.1
polish-roberta-8k-6L (progressive)
Size=216M
2026.03
80.95
EuroBERT/EuroBERT-210m
Size=212M
2026.03
80.42
sdadas/polish-roberta-base-v2
Size=124M
2026.03
77.3
allegro/herbert-base-cased
Size=124M
2026.03
77.08
FacebookAI/xlm-roberta-base
Size=278M
2026.03
74.42
Feedback
Search any
task
Search any
task