Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Problem Solving on MATH-Perturb MP-simple
Loading...
72.8
Exact Match Accuracy
DeepMath (GRPO)
16.432
31.066
45.7
60.334
Feb 1, 2026
Exact Match Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Exact Match Accuracy
DeepMath (GRPO)
Optimization=GRPO
2026.02
72.8
DeepMath (RULES)
Optimization=RULES
2026.02
72.8
DeepMath (vanilla)
Optimization=vanilla
2026.02
72
Qwen2.5 (RULES)
Optimization=RULES
2026.02
62.4
Qwen2.5 (vanilla)
Optimization=vanilla
2026.02
59.5
Qwen2.5 (GRPO)
Optimization=GRPO
2026.02
59.5
Llama-3.1 (vanilla)
Optimization=vanilla
2026.02
38.7
Llama-3.1 (RULES)
Optimization=RULES
2026.02
36.9
Llama-3.1 (GRPO)
Optimization=GRPO
2026.02
36.2
OLMO2 (RULES)
Optimization=RULES
2026.02
23.3
OLMO2 (GRPO)
Optimization=GRPO
2026.02
21.9
OLMO2 (vanilla)
Optimization=vanilla
2026.02
18.6
Feedback
Search any
task
Search any
task