# Mathematical Reasoning on AIME 2025 (Pass@k and Voting Metrics) Source: [Mathematical Reasoning on AIME 2025 (Pass@k and Voting Metrics)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:57:25.889Z Evaluation of model performance on the American Invitational Mathematics Examination (AIME) 2025 dataset, reporting results across various sampling strategies including Pass@k and voting mechanisms. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Mathematical Reasoning | | Dataset (including any stated split) | AIME 2025 | | Metric | Pass@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Pass@1](): Higher is better; unit: PERCENT. - [Majority Voting@8](): Higher is better; unit: PERCENT. - [Best-of-8](): Higher is better; unit: PERCENT. - [Verifier Voting@8](): Higher is better; unit: PERCENT. - [Pass@8](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pass@1 | Result date | Report paper | | --- | --- | --- | --- | | Qwen3-235B-A22B-Thinking-2507 | 95.4 | Not recorded | 693ba1796cfd488761a55186 | | gpt-oss-120b | 92.3 | Not recorded | 693ba1796cfd488761a55186 | | DeepSeek-R1-0528 | 87.1 | Not recorded | 693ba1796cfd488761a55186 | | QwQ-32B | 70 | Not recorded | 693ba1796cfd488761a55186 | | DeepSeek-R1-Distill-Qwen-32B | 55.9 | Not recorded | 693ba1796cfd488761a55186 | | DeepSeek-R1-Distill-Llama-70B | 44 | Not recorded | 693ba1796cfd488761a55186 | | DeepSeek-R1-Distill-Qwen-7B | 39.1 | Not recorded | 693ba1796cfd488761a55186 | ### Qwen3-235B-A22B-Thinking-2507 Pass@1: 95.4. Result ID: 6996c36f5698665ec40ec537. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"Qwen3-235B-A22B-Thinking-2507"}. This record does not assert independent reproduction. ### gpt-oss-120b Pass@1: 92.3. Result ID: 6996c36f5698665ec40ec535. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"gpt-oss-120b"}. This record does not assert independent reproduction. ### DeepSeek-R1-0528 Pass@1: 87.1. Result ID: 6996c36f5698665ec40ec534. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"DeepSeek-R1-0528"}. This record does not assert independent reproduction. ### QwQ-32B Pass@1: 70. Result ID: 6996c36f5698665ec40ec536. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"QwQ-32B"}. This record does not assert independent reproduction. ### DeepSeek-R1-Distill-Qwen-32B Pass@1: 55.9. Result ID: 6996c36f5698665ec40ec532. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"DeepSeek-R1-Distill-Qwen-32B"}. This record does not assert independent reproduction. ### DeepSeek-R1-Distill-Llama-70B Pass@1: 44. Result ID: 6996c36f5698665ec40ec533. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"DeepSeek-R1-Distill-Llama-70B"}. This record does not assert independent reproduction. ### DeepSeek-R1-Distill-Qwen-7B Pass@1: 39.1. Result ID: 6996c36f5698665ec40ec531. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Policy":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.