Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Advanced Mathematical Reasoning on Math500 (512 tokens)
Loading...
46.3
Pass@1 Accuracy
d-TreeRPO
34.34
37.445
40.55
43.655
Dec 10, 2025
Pass@1 Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Pass@1 Accuracy
d-TreeRPO
Base Model=LLaDA-MoE-7...
2025.12
46.3
TraceRL
Base Model=LLaDA-MoE-7...
2025.12
44.1
Diffu-GRPO
Base Model=LLaDA-MoE-7...
2025.12
43.4
wd1
Base Model=LLaDA-MoE-7...
2025.12
43.4
LLaDA-MoE-7BA1B-Instruct
Base Model=LLaDA-MoE-7...
2025.12
42.2
GDPO
Base Model=LLaDA-MoE-7...
2025.12
41.2
SAPO
Base Model=LLaDA-MoE-7...
2025.12
40.4
TraceRL
Base Model=LLaDA-8B-In...
2025.12
39.1
Diffu-GRPO
Base Model=LLaDA-8B-In...
2025.12
39
wd1
Base Model=LLaDA-8B-In...
2025.12
39
d-TreeRPO
Base Model=LLaDA-8B-In...
2025.12
38.9
GDPO
Base Model=LLaDA-8B-In...
2025.12
38.5
SAPO
Base Model=LLaDA-8B-In...
2025.12
38.4
LLaDA-8B-Instruct
Base Model=LLaDA-8B-In...
2025.12
36.2
VRPO (LLaDA-1.5)
Base Model=LLaDA-8B-In...
2025.12
34.8
Feedback
Search any
task
Search any
task