Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Downstream Evaluation on LM-Eval Harness (ARC-E, BoolQ, HellaSwag, OBQA, SciQ)
Loading...
0.381
ARC-E Accuracy
DDP
0.37476
0.37638
0.378
0.37962
Jul 11, 2025
ARC-E Accuracy
BoolQ Accuracy
HellaSwag Accuracy
OBQA Accuracy
SciQ Accuracy
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
ARC-E Accuracy
BoolQ Accuracy
HellaSwag Accuracy
OBQA Accuracy
SciQ Accuracy
Average Score
DDP
C (coverage ratio)=1.0...
2025.07
0.381
0.61
0.409
0.344
0.496
0.448
Bb-SDP
C (coverage ratio)=0.6...
2025.07
0.381
0.621
0.415
0.32
0.496
0.447
B-SDP
C (coverage ratio)=0.6...
2025.07
0.38
0.621
0.415
0.364
0.507
0.457
N-SDP
C (coverage ratio)=0.6...
2025.07
0.375
0.6
0.419
0.344
0.491
0.446
Feedback
Search any
task
Search any
task