ResearchBenchmarksFeasible Certification on BiochemFollow0.8Certification Success RatePHACT0.760.780.80.82Jun 29, 2026Evaluation ResultsMethodMethodLinksCertification Success RateLoop-fail CountWrong Verdict CountTimeout CountPHACTModel=Gemini 2.5 Flash...Model=Gemini 2.5 Flash, Temperature=02026.060.8200