Mathematical Reasoning on HMMT 2025 (Nov)
87.9Pass@1Pass@1
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Pass@1N=24, Backbone=GPT-OSS-20B2026.05 | 87.9 | — | — | — | — | — | |
| Pass@1N=48, Backbone=GPT-OSS-20B2026.05 | 87.9 | — | — | — | — | — | |
| Pass@1N=120, Backbone=GPT-OSS-20B2026.05 | 87.9 | — | — | — | — | — | |
| BoNN=24, Backbone=GPT-OSS-20B2026.05 | — | 90.9 | — | — | — | — | |
| BoNN=48, Backbone=GPT-OSS-20B2026.05 | — | 91 | — | — | — | — | |
| BoNN=120, Backbone=GPT-OSS-20B2026.05 | — | 90.4 | — | — | — | — | |
| JCN=24, Backbone=GPT-OSS-20B2026.05 | — | — | — | — | — | 93.7 | |
| JCN=48, Backbone=GPT-OSS-20B2026.05 | — | — | — | — | — | 94.1 | |
| JCN=120, Backbone=GPT-OSS-20B2026.05 | — | — | — | — | — | 94 | |
| KTN=24, Backbone=GPT-OSS-20B2026.05 | — | — | 31 | — | — | — | |
| KTN=48, Backbone=GPT-OSS-20B2026.05 | — | — | 32.9 | — | — | — | |
| KTN=120, Backbone=GPT-OSS-20B2026.05 | — | — | 30.4 | — | — | — | |
| SCN=24, Backbone=GPT-OSS-20B2026.05 | — | — | — | 93.3 | — | — | |
| SCN=48, Backbone=GPT-OSS-20B2026.05 | — | — | — | 93.8 | — | — | |
| SCN=120, Backbone=GPT-OSS-20B2026.05 | — | — | — | 93.7 | — | — | |
| WSCN=24, Backbone=GPT-OSS-20B2026.05 | — | — | — | — | 93.3 | — | |
| WSCN=48, Backbone=GPT-OSS-20B2026.05 | — | — | — | — | 93.9 | — | |
| WSCN=120, Backbone=GPT-OSS-20B2026.05 | — | — | — | — | 93.9 | — |