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

Reasoning on AIME 2024 (Speedup, Mean acceptance length τ)

7.35Speedup

DFlash+DDTree

2.95084.09295.2356.3771Apr 14, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
7.3510.42
2026.04
7.2710.37
2026.04
5.937.87
2026.04
5.567.54
2026.04
5.387.46
2026.04
5.367.79
2026.04
5.317.82
2026.04
4.947.32
2026.04
3.955.16
2026.04
3.55.01
2026.04
3.464.98
2026.04
3.124.23