Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Reasoning on MuSR
Loading...
71.89
Accuracy
LLaDA2.1-mini
43.7892
51.0846
58.38
65.6754
Feb 1, 2026
Feb 2, 2026
Feb 3, 2026
Feb 5, 2026
Feb 6, 2026
Feb 7, 2026
Feb 9, 2026
Accuracy
TPF
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
TPF
LLaDA2.1-mini
mode=Q Mode
2026.02
71.89
1.56
LLaDA2.0-mini
2026.02
71.48
1.45
Ling-mini-2.0
2026.02
71.36
-
LLaDA2.1-mini
mode=S Mode
2026.02
70.43
2.48
Qwen3-8B
no think=true
2026.02
70.02
-
Qwen3-4B
Loss function=base+aux
2026.02
55.46
-
Qwen3-4B
Loss function=base
2026.02
54.14
-
Qwen3-8B
Loss function=base+aux
2026.02
53.5
-
Qwen3-8B
Loss function=base
2026.02
49.78
-
LLaMA3.1-8B
Loss function=base+aux
2026.02
46.17
-
LLaMA3.1-8B
Loss function=base
2026.02
44.87
-
Feedback
Search any
task
Search any
task