Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on HotPot D2 (test)
Loading...
96.1
Macro F1
SURGELLM-S-DistilBERT
93.292
94.021
94.75
95.479
Jun 23, 2026
Macro F1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Macro F1
SURGELLM-S-DistilBERT
Family=SURGELLM-S, Par...
2026.06
96.1
SURGELLM-FULL-ALBERT
Family=SURGELLM-FULL,...
2026.06
96.1
SURGELLM-IWN-RoBERTa
Family=IWN, Parameters...
2026.06
95.4
SURGELLM-FULL-RoBERTa
Family=SURGELLM-FULL,...
2026.06
95
SURGELLM-G-RoBERTa
Family=SURGELLM-G, Par...
2026.06
94.9
Baseline-RoBERTa
Family=Baseline, Param...
2026.06
94.7
SURGELLM-IWN-BERT
Family=IWN, Parameters...
2026.06
94.6
Baseline-DistilBERT
Family=Baseline, Param...
2026.06
94
T5-base
Family=T5-T2T, Paramet...
2026.06
93.9
SURGELLM-S-BERT
Family=SURGELLM-S, Par...
2026.06
93.9
Baseline-BERT
Family=Baseline, Param...
2026.06
93.4
Feedback
Search any
task
Search any
task