Algorithm Correctness on ALGOGEN-Bench 1.0 (test)
99.8Algorithm CorrectnessALGOGEN
Evaluation Results
| Method | Links | |
|---|---|---|
| ALGOGENVTA component=Enabled, RSL component=Enabled2026.05 | 99.8 | |
| ALGOGENVTA component=Enabled, RSL component=Disabled2026.05 | 99.2 | |
| manim_directVTA component=Enabled2026.05 | 87 | |
| manim_direct_novtaVTA component=Disabled2026.05 | 84.9 |