Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Natural Language Reasoning on BoolQ, ARC-e, ARC-c, WinoGrande, HellaSwag
Loading...
75.2
BoolQ Accuracy
MoEITS
68.2944
70.0872
71.88
73.6728
Apr 12, 2026
BoolQ Accuracy
ARC-e Accuracy
ARC-c Accuracy
WinoGrande Accuracy
HellaSwag Accuracy
Average Accuracy
Updated 5d ago
Evaluation Results
Method
Method
Links
BoolQ Accuracy
ARC-e Accuracy
ARC-c Accuracy
WinoGrande Accuracy
HellaSwag Accuracy
Average Accuracy
MoEITS
Base Model=Qwen1.5-2.7...
2026.04
75.2
72.3
36.01
67.46
61.27
62.45
MoE-I^2
Base Model=Qwen1.5-2.7...
2026.04
75.08
71.68
41.13
66.54
53.08
61.5
MoE-Pruner
Base Model=Qwen1.5-2.7...
2026.04
69.14
52.02
29.1
59.12
42.99
50.47
MoP
Base Model=Qwen1.5-2.7...
2026.04
68.56
59.76
44.97
52.57
56.4
56.45
Feedback
Search any
task
Search any
task