Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning Repair on GSM8K (test)
Loading...
1,162
Pass Count
Direct
982.08
1,028.79
1,075.5
1,122.21
May 25, 2026
Pass Count
Fail Count
Repair Success Rate
Minimum Performance Score
Updated 8d ago
Evaluation Results
Method
Method
Links
Pass Count
Fail Count
Repair Success Rate
Minimum Performance Score
Direct
Total=1319
2026.05
1,162
157
0
1
Self-Reflection
Total=1319
2026.05
1,155
164
35
0.88
Self-Refine
Total=1319
2026.05
1,148
171
5
0.99
CausalFlow
Total=1319
2026.05
989
330
173
0.87
Feedback
Search any
task
Search any
task