Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on Math500 decontaminated (Accuracy)
Loading...
77.8
Accuracy
DAPO-Math-17k
47.224
55.162
63.1
71.038
May 26, 2026
Accuracy
Updated 7d ago
Evaluation Results
Method
Method
Links
Accuracy
DAPO-Math-17k
Backbone=Qwen3-8B, RLV...
2026.05
77.8
DAPO++
Backbone=Qwen3-8B, Sam...
2026.05
77.7
DeepScaleR
Backbone=Qwen3-8B, RLV...
2026.05
75.9
DeepMath-103K
Backbone=Qwen3-8B, RLV...
2026.05
73.4
Skywork-OR1-RL-Data
Backbone=Qwen3-8B, RLV...
2026.05
73.2
OpenR1-Math-220k
Backbone=Qwen3-8B, RLV...
2026.05
73.1
Qwen3-8B-Base
Backbone=Qwen3-8B, Sam...
2026.05
61.6
DAPO++
Backbone=Qwen3-1.7B, S...
2026.05
60
OpenR1-Math-220k
Backbone=Qwen3-1.7B, R...
2026.05
58.9
Skywork-OR1-RL-Data
Backbone=Qwen3-1.7B, R...
2026.05
58.8
DAPO-Math-17k
Backbone=Qwen3-1.7B, R...
2026.05
58.5
DeepScaleR
Backbone=Qwen3-1.7B, R...
2026.05
58.1
DeepMath-103K
Backbone=Qwen3-1.7B, R...
2026.05
57.9
Qwen3-1.7B-Base
Backbone=Qwen3-1.7B, S...
2026.05
48.4
Feedback
Search any
task
Search any
task