Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-task Performance Evaluation on Multi-task Suite D1-D4 (test)
Loading...
94
Avg F1
SURGELLM-IWN-RoBERTa
86.72
88.61
90.5
92.39
Jun 23, 2026
Avg F1
Avg F1 Delta (vs RoBERTa Baseline)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg F1
Avg F1 Delta (vs RoBERTa Baseline)
SURGELLM-IWN-RoBERTa
Family=IWN, Parameters...
2026.06
94
0.036
SURGELLM-IWN-BERT
Family=IWN, Parameters...
2026.06
92.7
0.023
SURGELLM-G-RoBERTa
Family=SURGELLM-G, Par...
2026.06
90.6
0.002
Baseline-RoBERTa
Family=Baseline, Param...
2026.06
90.4
-
T5-base
Family=T5-T2T, Paramet...
2026.06
89.7
-0.007
Baseline-BERT
Family=Baseline, Param...
2026.06
89.4
-0.01
SURGELLM-S-BERT
Family=SURGELLM-S, Par...
2026.06
89.4
-0.01
SURGELLM-FULL-RoBERTa
Family=SURGELLM-FULL,...
2026.06
88.9
-0.015
Baseline-DistilBERT
Family=Baseline, Param...
2026.06
88.6
-0.018
SURGELLM-FULL-ALBERT
Family=SURGELLM-FULL,...
2026.06
88.6
-0.018
SURGELLM-S-DistilBERT
Family=SURGELLM-S, Par...
2026.06
87
-0.034
Feedback
Search any
task
Search any
task