Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Equation Deduction on The benchmark (held-out slice)
Loading...
95.1
Accuracy
Python Solver Oracle
-3.492
22.104
47.7
73.296
Jun 20, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Python Solver Oracle
type=reverse-engineere...
2026.06
95.1
Solver-Grounded Synthetic CoT (Model)
adapter=fine-tuned ran...
2026.06
83
Python Solver Oracle
type=backtracking / ge...
2026.06
71
Base Model
2026.06
28.7
Solver-Grounded Synthetic CoT (Model)
adapter=fine-tuned ran...
2026.06
1
Base Model
2026.06
0.3
Feedback
Search any
task
Search any
task