Mathematical Reasoning on AIME 2025 (OTPS, Accuracy, Drop)
186.5OTPSXShare
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| XSharewarm-up k0=1, batch budget ml=0, per-request budget mr=4, Batch Size=4, Speculation Length=32026.02 | 186.5 | 0.9 | 2.5 | |
| XSharewarm-up k0=2, batch budget ml=0, per-request budget mr=4, Batch Size=4, Speculation Length=32026.02 | 183.96 | 0.8667 | -0.83 | |
| XSharewarm-up k0=0, batch budget ml=4, per-request budget mr=16, Batch Size=4, Speculation Length=32026.02 | 180.81 | 0.6333 | -24.17 | |
| XSharewarm-up k0=0, batch budget ml=0, per-request budget mr=8, Batch Size=4, Speculation Length=32026.02 | 178.12 | 0.8667 | -0.83 | |
| XSharewarm-up k0=1, batch budget ml=0, per-request budget mr=5, Batch Size=4, Speculation Length=32026.02 | 176.95 | 0.9 | 2.5 | |
| XSharewarm-up k0=2, batch budget ml=10, per-request budget mr=0, Batch Size=4, Speculation Length=32026.02 | 174.6 | 0.9333 | 5.83 | |
| XSharewarm-up k0=1, batch budget ml=32, per-request budget mr=0, Batch Size=4, Speculation Length=32026.02 | 168.36 | 0.8667 | -0.83 | |
| XSharewarm-up k0=1, batch budget ml=24, per-request budget mr=0, Batch Size=4, Speculation Length=32026.02 | 168.25 | 0.9333 | 5.83 | |
| GPT-OSS 120B BaselineBatch Size=4, Speculation Length=32026.02 | 165.39 | 0.875 | — |