List your company

Planning on Countdown (held-out)

87.96Pass@1INSIGHT
70.914475.339779.76584.1903Mar 2, 2026

Evaluation results

MethodLinks
INSIGHTModel=QWEN3-4B2026.0387.96
MoPPSModel=QWEN3-4B2026.0387.8
RANDOMModel=QWEN3-4B2026.0384.9
INVERSE-EVIDENCEModel=QWEN3-4B2026.0383.59
DSModel=R1-DISTILL-QWEN-7B2026.0383.05
INSIGHTModel=R1-DISTILL-QWEN-7B2026.0381.73
MoPPSModel=R1-DISTILL-QWEN-7B2026.0381.66
EXPECTED-DIFFICULTYModel=R1-DISTILL-QWEN-7B2026.0381.2
RANDOMModel=R1-DISTILL-QWEN-7B2026.0379.02
INVERSE-EVIDENCEModel=R1-DISTILL-QWEN-7B2026.0378.32
INSIGHTModel=QWEN3-0.6B2026.0376.7
MoPPSModel=QWEN3-0.6B2026.0376.28
INVERSE-EVIDENCEModel=QWEN3-0.6B2026.0372.13
RANDOMModel=QWEN3-0.6B2026.0371.57