Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME 25 (Accuracy, Avg)
Loading...
12.3
Accuracy
GRPO + coupled rhythm credit
6.164
7.757
9.35
10.943
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
12.3
43.2
GRPO + global-anchor credit
Base Model=Qwen3-8B-Ba...
2025.10
11.5
42.1
GRPO + CAPO
Base Model=Qwen3-8B-Ba...
2025.10
10.9
41.4
GRPO + ThinkPRM-1.5B
Base Model=Qwen3-8B-Ba...
2025.10
10.6
41
GRPO + high-entropy selection
Base Model=Qwen3-8B-Ba...
2025.10
10.5
40.9
GRPO + local-chunk credit
Base Model=Qwen3-8B-Ba...
2025.10
9.3
41.3
GRPO + gradient-based credit
Base Model=Qwen3-8B-Ba...
2025.10
9.2
40
GRPO + path-aggregation credit
Base Model=Qwen3-8B-Ba...
2025.10
9.1
40
GRPO + Reweight+Lopti
Base Model=Qwen3-8B-Ba...
2025.10
8.8
41.1
GRPO + AsyPPO
Base Model=Qwen3-8B-Ba...
2025.10
8.2
40
GRPO + random credit
Base Model=Qwen3-8B-Ba...
2025.10
8.1
39.6
GRPO + high-entropy credit
Base Model=Qwen3-8B-Ba...
2025.10
7.7
40.1
GRPO
Base Model=Qwen3-8B-Ba...
2025.10
7.3
39.4
GRPO + token-correlation credit
Base Model=Qwen3-8B-Ba...
2025.10
6.4
37.4
Feedback
Search any
task
Search any
task