Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Self-awareness on SelfAware
Loading...
51.2
Accuracy
Base Model
31.752
36.801
41.85
46.899
Jan 22, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Base Model
Backbone=Qwen2.5-7B
2026.01
51.2
CARE-GSPO
Backbone=Qwen2.5-7B
2026.01
50.2
RKL-GSPO
Backbone=Qwen2.5-7B
2026.01
49.8
CARE-GRPO
Backbone=Qwen2.5-7B
2026.01
49.5
RKL-GRPO
Backbone=Qwen2.5-7B
2026.01
49.1
CARE-DAPO
Backbone=Qwen2.5-7B
2026.01
49.1
RKL-DAPO
Backbone=Qwen2.5-7B
2026.01
48.7
GRPO (No Constraint)
Backbone=Qwen2.5-7B
2026.01
35.3
GSPO (No Constraint)
Backbone=Qwen2.5-7B
2026.01
32.7
DAPO (No Constraint)
Backbone=Qwen2.5-7B
2026.01
32.5
Feedback
Search any
task
Search any
task