Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (PTR adv., ReAct adv., Avg. ∆EM)
Loading...
3
PTR Advancement Accuracy
PTR
2.85
2.925
3
3.075
Apr 5, 2026
PTR Advancement Accuracy
ReAct Advancement Accuracy
Average Error Margin (∆EM)
Updated 12d ago
Evaluation Results
Method
Method
Links
PTR Advancement Accuracy
ReAct Advancement Accuracy
Average Error Margin (∆EM)
PTR
Average over=4 models
2026.04
3
1
0.129
ReAct
Average over=4 models
2026.04
3
1
0.129
Feedback
Search any
task
Search any
task