Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on SVAMP (Acc, SL, SE)
Loading...
96.7
Accuracy
L1
85.156
88.153
91.15
94.147
Mar 23, 2026
Apr 1, 2026
Apr 11, 2026
Apr 20, 2026
Apr 30, 2026
May 9, 2026
May 19, 2026
Accuracy
Solution Length (SL)
Solution Error (SE)
Updated 14d ago
Evaluation Results
Method
Method
Links
Accuracy
Solution Length (SL)
Solution Error (SE)
L1
2026.03
96.7
1,138
8.5
Cut1024
max tokens=1024
2026.03
96.67
1,872
5.16
ROM_CSC
Counterfactual Self-Co...
2026.03
95.8
906
10.57
Vanilla
2026.03
95
1,874
5.07
EAT
2026.03
95
1,480
6.42
Cut2048
max tokens=2048
2026.03
95
1,872
5.07
ROM
2026.03
92.5
1,241
7.45
Cut512
max tokens=512
2026.03
86.67
1,872
4.63
CES
Backbone=DeepSeek-R1-D...
2026.05
86.4
620
-
DAPO
Backbone=DeepSeek-R1-D...
2026.05
85.6
618
-
Feedback
Search any
task
Search any
task