Specialized prompt ensembles let 35B open-source models verify math proofs on par with frontier LLMs like Gemini 3.1 Pro.
After your analysis: \boxed{INCORRECT} if you found a specific flaw; \boxed{CORRECT} if your best skeptical effort found none
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Do We Need Frontier Models to Verify Mathematical Proofs?
Specialized prompt ensembles let 35B open-source models verify math proofs on par with frontier LLMs like Gemini 3.1 Pro.