Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on MATH (Accuracy, Avg)
Loading...
79.7
Accuracy
GRPO + coupled rhythm credit
76.268
77.159
78.05
78.941
Oct 15, 2025
Accuracy
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Average Score
GRPO + coupled rhythm credit
Base Model=Qwen3-8B-Ba...
2025.10
79.7
43.2
GRPO + global-anchor credit
Base Model=Qwen3-8B-Ba...
2025.10
78.9
42.1
GRPO + Reweight+Lopti
Base Model=Qwen3-8B-Ba...
2025.10
78.6
41.1
GRPO + CAPO
Base Model=Qwen3-8B-Ba...
2025.10
78.4
41.4
GRPO + local-chunk credit
Base Model=Qwen3-8B-Ba...
2025.10
78.4
41.3
GRPO + high-entropy credit
Base Model=Qwen3-8B-Ba...
2025.10
78
40.1
GRPO + gradient-based credit
Base Model=Qwen3-8B-Ba...
2025.10
78
40
GRPO + AsyPPO
Base Model=Qwen3-8B-Ba...
2025.10
77.8
40
GRPO + high-entropy selection
Base Model=Qwen3-8B-Ba...
2025.10
77.6
40.9
GRPO + ThinkPRM-1.5B
Base Model=Qwen3-8B-Ba...
2025.10
77.6
41
GRPO + random credit
Base Model=Qwen3-8B-Ba...
2025.10
77.4
39.6
GRPO + path-aggregation credit
Base Model=Qwen3-8B-Ba...
2025.10
77.3
40
GRPO
Base Model=Qwen3-8B-Ba...
2025.10
77.1
39.4
GRPO + token-correlation credit
Base Model=Qwen3-8B-Ba...
2025.10
76.4
37.4
Feedback
Search any
task
Search any
task