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

Reasoning Performance Aggregation on Aggregate Benchmarks Code Math

56.2Code Component Average

SAGE

46.52849.03951.5554.061Mar 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
56.255.855.9
2026.03
55.547.550.1
2026.03
55.246.849.6
2026.03
55.246.749.5
2026.03
55.253.954.4
2026.03
54.94548.3
2026.03
54.556.355.7
2026.03
5245.447.6
2026.03
49.438.342
2026.03
48.435.739.9
2026.03
48.436.640.5
2026.03
46.937.240.4