Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on MATH-500 (test)
Loading...
32.16
Error Rate
G-PAC
31.9552
33.3376
34.72
36.1024
Jan 30, 2026
Error Rate
ErrorGap
STP
Updated 4d ago
Evaluation Results
Method
Method
Links
Error Rate
ErrorGap
STP
G-PAC
Score type=Logits-base...
2026.01
32.16
0
2.91
G-PAC
Score type=Verbalized...
2026.01
32.18
0
-2.21
G-PAC
Score type=Router-base...
2026.01
32.99
0
23.04
PAC
Score type=Verbalized...
2026.01
36.52
12.47
11.32
PAC
Score type=Router-base...
2026.01
37.17
16.2
26.01
PAC
Score type=Logits-base...
2026.01
37.28
19.27
12.55
Feedback
Search any
task
Search any
task