Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Expression Synthesis on GSM-Symbolic (test)
Loading...
66
Accuracy (%)
SEVerA
37.192
44.671
52.15
59.629
Mar 26, 2026
Accuracy (%)
Violation Rate (%)
Inference Time (s)
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy (%)
Violation Rate (%)
Inference Time (s)
SEVerA
Parameter tuning=with,...
2026.03
66
0
16.7
SEVerA
Parameter tuning=no, b...
2026.03
53.2
0
18.8
CRANE
base_model=Qwen3-8B
2026.03
44.7
2.1
12.4
LLM (Qwen3-8B)
base_model=Qwen3-8B
2026.03
38.3
10.6
10.9
Feedback
Search any
task
Search any
task