Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on Olympiad decontaminated (Accuracy)
Loading...
43.5
Accuracy
DAPO++
16.564
23.557
30.55
37.543
May 26, 2026
Accuracy
Updated 7d ago
Evaluation Results
Method
Method
Links
Accuracy
DAPO++
Backbone=Qwen3-8B, Sam...
2026.05
43.5
DAPO-Math-17k
Backbone=Qwen3-8B, Sam...
2026.05
43
DeepMath-103K
Backbone=Qwen3-8B, Sam...
2026.05
39.2
DeepScaleR
Backbone=Qwen3-8B, Sam...
2026.05
38.8
Skywork-OR1-RL-Data
Backbone=Qwen3-8B, Sam...
2026.05
37.8
OpenR1-Math-220k
Backbone=Qwen3-8B, Sam...
2026.05
37
Qwen3-8B-Base
Backbone=Qwen3-8B, Sam...
2026.05
27.9
DAPO++
Backbone=Qwen3-1.7B, S...
2026.05
24.9
Skywork-OR1-RL-Data
Backbone=Qwen3-1.7B, S...
2026.05
24.7
OpenR1-Math-220k
Backbone=Qwen3-1.7B, S...
2026.05
24
DeepScaleR
Backbone=Qwen3-1.7B, S...
2026.05
23.7
DeepMath-103K
Backbone=Qwen3-1.7B, S...
2026.05
23.1
DAPO-Math-17k
Backbone=Qwen3-1.7B, S...
2026.05
22.9
Qwen3-1.7B-Base
Backbone=Qwen3-1.7B, S...
2026.05
17.6
Feedback
Search any
task
Search any
task