List your company

Science Question Answering on ARC (Verifiability Score)

81.19Verifiability ScoreR1
28.576442.235755.89569.5543Feb 19, 2026

Evaluation results

MethodLinks
R1Executor=Strong Comm.2026.0281.19
PhiExecutor=Strong Comm.2026.0276.62
PhiExecutor=Full Comm.2026.0269.7
GemmaExecutor=Strong Comm.2026.0268.99
LlamaExecutor=Strong Comm.2026.0263.96
PhiExecutor=Weak Comm.2026.0262.78
R1Executor=Full Comm.2026.0262.61
GemmaExecutor=Full Comm.2026.0249.9
LlamaExecutor=Full Comm.2026.0247.28
R1Executor=Weak Comm.2026.0244.03
GemmaExecutor=Weak Comm.2026.0230.8
LlamaExecutor=Weak Comm.2026.0230.6