Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Open Question Answering on AIME 2025 (test)

70Accuracy

GRPO

24.936836.635948.33560.0341Feb 10, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
709,871
2026.02
703,788
2026.02
66.677,841
2026.02
66.676,504
2026.02
66.674,513
2026.02
66.677,324
2026.02
66.673,045
2026.02
66.673,413
2026.02
26.671,513