Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on MATH-500 (VAcc, RAcc, Delta Acc, TFR)
Loading...
83.2
VAcc (Verification Accuracy)
MASTER
25.168
40.234
55.3
70.366
Jun 5, 2025
VAcc (Verification Accuracy)
RAcc (Rerun Accuracy)
Delta Acc (Delta Accuracy)
TFR (Token Frequency Ratio)
Updated 1mo ago
Evaluation Results
Method
Method
Links
VAcc (Verification Accuracy)
RAcc (Rerun Accuracy)
Delta Acc (Delta Accuracy)
TFR (Token Frequency Ratio)
MASTER
Target model=DeepSeek-...
2025.06
83.2
31
52.2
62.74
MASTER
Target model=Qwen2.5-M...
2025.06
81.6
44.2
37.4
45.83
MASTER
Target model=LLaMA-3.2...
2025.06
29.8
3.4
26.4
88.59
MASTER
Target model=LLaMA-3-8...
2025.06
29.2
6
23.2
79.45
MASTER
Target model=Gemma-2-2...
2025.06
27.4
3.8
23.6
86.13
Feedback
Search any
task
Search any
task
