Mathematical Reasoning on BRUMO 2025 (Pass@1, BoN, KT, SC, WSC, JC)
86.2Pass@1Pass@1
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Pass@1N=48, Backbone=GPT-OSS-20B2026.05 | 86.2 | — | — | — | — | — | |
| Pass@1N=24, Backbone=GPT-OSS-20B2026.05 | 86.1 | — | — | — | — | — | |
| Pass@1N=120, Backbone=GPT-OSS-20B2026.05 | 86.1 | — | — | — | — | — | |
| BoNN=24, Backbone=GPT-OSS-20B2026.05 | — | 91.5 | — | — | — | — | |
| BoNN=48, Backbone=GPT-OSS-20B2026.05 | — | 91 | — | — | — | — | |
| BoNN=120, Backbone=GPT-OSS-20B2026.05 | — | 90.6 | — | — | — | — | |
| JCN=24, Backbone=GPT-OSS-20B2026.05 | — | — | — | — | — | 99.5 | |
| JCN=48, Backbone=GPT-OSS-20B2026.05 | — | — | — | — | — | 99.8 | |
| JCN=120, Backbone=GPT-OSS-20B2026.05 | — | — | — | — | — | 100 | |
| KTN=24, Backbone=GPT-OSS-20B2026.05 | — | — | 23.4 | — | — | — | |
| KTN=48, Backbone=GPT-OSS-20B2026.05 | — | — | 29.8 | — | — | — | |
| KTN=120, Backbone=GPT-OSS-20B2026.05 | — | — | 38.5 | — | — | — | |
| SCN=24, Backbone=GPT-OSS-20B2026.05 | — | — | — | 97.3 | — | — | |
| SCN=48, Backbone=GPT-OSS-20B2026.05 | — | — | — | 97.8 | — | — | |
| SCN=120, Backbone=GPT-OSS-20B2026.05 | — | — | — | 98.7 | — | — | |
| WSCN=24, Backbone=GPT-OSS-20B2026.05 | — | — | — | — | 99 | — | |
| WSCN=48, Backbone=GPT-OSS-20B2026.05 | — | — | — | — | 99.7 | — | |
| WSCN=120, Backbone=GPT-OSS-20B2026.05 | — | — | — | — | 100 | — |