Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Equation Number Guessing on The benchmark (held-out slice)
Loading...
59
Accuracy
Python Solver Oracle
-2.36
13.57
29.5
45.43
Jun 20, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Python Solver Oracle
type=backtracking / ge...
2026.06
59
Python Solver Oracle
type=reverse-engineere...
2026.06
20.6
Solver-Grounded Synthetic CoT (Model)
adapter=fine-tuned ran...
2026.06
18
Base Model
2026.06
3.7
Solver-Grounded Synthetic CoT (Model)
adapter=fine-tuned ran...
2026.06
2
Base Model
2026.06
0
Feedback
Search any
task
Search any
task