Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Step-level classification on ProcessBench (test)
Loading...
75.1
F1 Score
MCNIG
39.74
48.92
58.1
67.28
Mar 18, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
MCNIG
model size=14B
2026.03
75.1
QwenPRM
model size=7B
2026.03
75
MCNIG
model size=8B
2026.03
73.2
IG
model size=8B
2026.03
70.1
Granite PRM v2
2026.03
51.9
MathShepherd
2026.03
41.1
Feedback
Search any
task
Search any
task