List your company

Counterexample generation on VERI-REASON

213Pass@1Ours
-4.3652.07108.5164.93Mar 19, 2026

Evaluation results

MethodLinks
OursConfig=fine-tuned2026.03213260295
Leanabell-proverCategory=OPEN-SOURCED NEURAL PROVERS2026.03144210231
Deepseek-prover-v2Category=OPEN-SOURCED NEURAL PROVERS2026.03144203234
STP-proverCategory=OPEN-SOURCED NEURAL PROVERS2026.03131151170
Goedel-prover-v2Category=OPEN-SOURCED NEURAL PROVERS2026.0388147200
Kimina-prover-distillCategory=OPEN-SOURCED NEURAL PROVERS2026.0366114156
GPT-4.1-miniCategory=PROPRIETARY REASONING MODELS2026.035497150
Deepseek-R1Category=PROPRIETARY REASONING MODELS2026.035175105
Gemini-2.5-FlashCategory=PROPRIETARY REASONING MODELS2026.035915
Grok-3-miniCategory=PROPRIETARY REASONING MODELS2026.0341019