Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
General Knowledge on HellaSwag
Loading...
59.4
Accuracy
Qwen3-1.7B
-1.88928
14.02236
29.934
45.84564
Feb 18, 2025
Apr 19, 2025
Jun 18, 2025
Aug 17, 2025
Oct 16, 2025
Dec 15, 2025
Feb 14, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen3-1.7B
Model Size=1.7B, Archi...
2026.02
59.4
Qwen3-1.7B-ALLMEM
Model Size=1.7B, Archi...
2026.02
59.4
Qwen3-0.6B-ALLMEM
Model Size=0.6B, Archi...
2026.02
41.4
Qwen3-0.6B
Model Size=0.6B, Archi...
2026.02
40.8
Chat
Use Sens=false, Backbo...
2025.02
0.6597
Task Arithmetic
Use Sens=true, Backbon...
2025.02
0.6194
DARE
Use Sens=true, Backbon...
2025.02
0.5892
Math
Use Sens=false, Backbo...
2025.02
0.5868
Ties-Merging
Use Sens=true, Backbon...
2025.02
0.5794
Ties-Merging
Use Sens=false, Backbo...
2025.02
0.5759
DARE
Use Sens=false, Backbo...
2025.02
0.5577
Code
Use Sens=false, Backbo...
2025.02
0.5319
Task Arithmetic
Use Sens=false, Backbo...
2025.02
0.468
Feedback
Search any
task
Search any
task