Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on Minerva decontaminated (Accuracy)
Loading...
37.1
Accuracy
DAPO++
14.428
20.314
26.2
32.086
May 26, 2026
Accuracy
Updated 7d ago
Evaluation Results
Method
Method
Links
Accuracy
DAPO++
Backbone=Qwen3-8B, Sam...
2026.05
37.1
DAPO-Math-17k
Backbone=Qwen3-8B, Sam...
2026.05
36.7
OpenR1-Math-220k
Backbone=Qwen3-8B, Sam...
2026.05
35.7
DeepScaleR
Backbone=Qwen3-8B, Sam...
2026.05
34.7
Skywork-OR1-RL-Data
Backbone=Qwen3-8B, Sam...
2026.05
34.5
DeepMath-103K
Backbone=Qwen3-8B, Sam...
2026.05
31.9
DeepMath-103K
Backbone=Qwen3-1.7B, S...
2026.05
26.5
Qwen3-8B-Base
Backbone=Qwen3-8B, Sam...
2026.05
25.6
DeepScaleR
Backbone=Qwen3-1.7B, S...
2026.05
23.3
OpenR1-Math-220k
Backbone=Qwen3-1.7B, S...
2026.05
23.1
Skywork-OR1-RL-Data
Backbone=Qwen3-1.7B, S...
2026.05
22.8
DAPO-Math-17k
Backbone=Qwen3-1.7B, S...
2026.05
22.6
DAPO++
Backbone=Qwen3-1.7B, S...
2026.05
21.9
Qwen3-1.7B-Base
Backbone=Qwen3-1.7B, S...
2026.05
15.3
Feedback
Search any
task
Search any
task