Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
General Language Understanding on CMMLU
Loading...
77.3
Overall Accuracy
NBDiff-7B-BASE
54.0664
60.0982
66.13
72.1618
Dec 7, 2025
Dec 12, 2025
Dec 17, 2025
Dec 22, 2025
Dec 27, 2025
Jan 1, 2026
Jan 6, 2026
Overall Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Overall Accuracy
NBDiff-7B-BASE
Configuration=Base
2025.12
77.3
LLaDA-8B
Configuration=Base
2025.12
69.9
LLaDA-MoE-7B
Configuration=A1B-Base
2025.12
65.7
Dream-v0
Configuration=Base-7B
2025.12
60.9
InfLLM v2
Training Tokens=100B,...
2026.01
55.9
InfLLM v2
Training Tokens=100B,...
2026.01
55.53
InfLLM v2
Training Tokens=100B,...
2026.01
55.51
InfLLM v2
Training Tokens=100B,...
2026.01
55.48
Dense
Training Tokens=100B,...
2026.01
55.44
Dense
Training Tokens=100B,...
2026.01
55.38
PHSA
Training Tokens=100B,...
2026.01
55.23
PHSA
Training Tokens=100B,...
2026.01
55.16
PHSA
Training Tokens=100B,...
2026.01
55.16
PHSA
Training Tokens=100B,...
2026.01
54.96
Feedback
Search any
task
Search any
task