List your company

General Reasoning on ARC, BBH, DROP, CommonsenseQA, SIQA

79CBRC ScoreARC
70.6872.847577.16Jan 7, 2026

Evaluation results

MethodLinks
ARCPrompting=Standardized templates, Decoding=Greedy, Evaluation Metric=Exact match or execution-based2026.01790.03115,6950.07870.0565
BBHPrompting=Standardized templates, Decoding=Greedy, Evaluation Metric=Exact match or execution-based2026.01750.02253,0890.12660.0560
CommonsenseQAPrompting=Standardized templates, Decoding=Greedy, Evaluation Metric=Exact match or execution-based2026.01750.07173,7850.11570.0254
SIQAPrompting=Standardized templates, Decoding=Greedy, Evaluation Metric=Exact match or execution-based2026.01730.05172,4530.09230.0340
DROPPrompting=Standardized templates, Decoding=Greedy, Evaluation Metric=Exact match or execution-based2026.01710.08204,1870.05610.0756