List your company

Mathematical Reasoning on AIME 2025 (OTPS, Accuracy, Drop)

186.5OTPSXShare
164.5456170.2453175.945181.6447Feb 6, 2026

Evaluation results

MethodLinks
XSharewarm-up k0=1, batch budget ml=0, per-request budget mr=4, Batch Size=4, Speculation Length=32026.02186.50.92.5
XSharewarm-up k0=2, batch budget ml=0, per-request budget mr=4, Batch Size=4, Speculation Length=32026.02183.960.8667-0.83
XSharewarm-up k0=0, batch budget ml=4, per-request budget mr=16, Batch Size=4, Speculation Length=32026.02180.810.6333-24.17
XSharewarm-up k0=0, batch budget ml=0, per-request budget mr=8, Batch Size=4, Speculation Length=32026.02178.120.8667-0.83
XSharewarm-up k0=1, batch budget ml=0, per-request budget mr=5, Batch Size=4, Speculation Length=32026.02176.950.92.5
XSharewarm-up k0=2, batch budget ml=10, per-request budget mr=0, Batch Size=4, Speculation Length=32026.02174.60.93335.83
XSharewarm-up k0=1, batch budget ml=32, per-request budget mr=0, Batch Size=4, Speculation Length=32026.02168.360.8667-0.83
XSharewarm-up k0=1, batch budget ml=24, per-request budget mr=0, Batch Size=4, Speculation Length=32026.02168.250.93335.83
GPT-OSS 120B BaselineBatch Size=4, Speculation Length=32026.02165.390.875—