Mathematical Reasoning on OlympiadBench (pass@1, pass@64) benchmark leaderboard · SOTA2 Research

Mathematical Reasoning on OlympiadBench (pass@1, pass@64)

9.78Pass@1DSTaR

Evaluation Results

Method	Links
DSTaR2026.05		9.78	41.83
DPólya2026.05		8.66	43.46
DPólya2026.05		8.45	43.57
DPólya2026.05		8.15	42.87
Zero-Shot2026.05		7.86	42.13
DPólya2026.05		7.72	42.47
DPólya2026.05		7.48	42.82
DPólya2026.05		7.34	42.57
DPólya2026.05		6.8	42.35