Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
First Incorrect Step Identification on MMMU, MathVision, MathVerse-VO, DynaMath, WeMath Overall
Loading...
26.4
FISI F1
TIM-PRM-8B
5.184
10.692
16.2
21.708
Nov 28, 2025
FISI F1
Updated 2d ago
Evaluation Results
Method
Method
Links
FISI F1
TIM-PRM-8B
Model=TIM-PRM-8B
2025.11
26.4
TIM-PRM-2B
Model=TIM-PRM-2B
2025.11
23.4
Qwen3-VL-8B
Model=Qwen3-VL-8B
2025.11
17.2
MM-PRM-8B
Model=MM-PRM-8B
2025.11
14.4
VisualPRM-8B
Model=VisualPRM-8B
2025.11
9.9
Qwen3-VL-2B
Model=Qwen3-VL-2B
2025.11
6
Feedback
Search any
task
Search any
task