Mathematical Reasoning on AIMO3 competition
43ScoreSTOP
Evaluation Results
| Method | Links | |
|---|---|---|
| STOPbase_model=GPT-OSS-120B, budget=16→82026.04 | 43 | |
| STOPbase_model=GPT-OSS-120B, budget=24→82026.04 | 42 | |
| Baseline + Toolbase_model=GPT-OSS-120B2026.04 | 39 |
| Method | Links | |
|---|---|---|
| STOPbase_model=GPT-OSS-120B, budget=16→82026.04 | 43 | |
| STOPbase_model=GPT-OSS-120B, budget=24→82026.04 | 42 | |
| Baseline + Toolbase_model=GPT-OSS-120B2026.04 | 39 |