Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning on GPQA (Error %, ErrorGap %, STP %)
Loading...
10.82
Error Rate (%)
G-PAC
10.7892
10.9971
11.205
11.4129
Jan 30, 2026
Error Rate (%)
ErrorGap (%)
STP (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Error Rate (%)
ErrorGap (%)
STP (%)
G-PAC
Scoring method=Verbali...
2026.01
10.82
0
19.6
PAC
Scoring method=Verbali...
2026.01
10.86
0
17.07
PAC
Scoring method=Logits-...
2026.01
11.24
30
8.73
G-PAC
Scoring method=Router-...
2026.01
11.34
0
30.54
PAC
Scoring method=Router-...
2026.01
11.57
0
34.21
G-PAC
Scoring method=Logits-...
2026.01
11.59
0
13.78
Feedback
Search any
task
Search any
task
