Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LLM Self-Consistency Certification on FrontierScience Olympiad

53Bonferroni Score

CITE/W-CITE Framework

17.95227.05136.1545.249May 7, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
5356.356.763.328.1160436.1439.2138.5
2026.05
42.944.945.353.624.5112.9195.5193.597
2026.05
42.947.542.855.920250.3494.7499.924.3
2026.05
3535.635.944.319.873.711011260.6
2026.05
3438.224.244.620172258.731924.3
2026.05
31.231.531.537.314.64665.564.335.9
2026.05
28.428.828.932.812.12837.940.922.9
2026.05
23.726.920.13320108.5144.6108.924.3
2026.05
20.521.318.825.519.965.167.640.424
2026.05
19.318.714.720.919.237.832.328.722.1