# Mathematical Reasoning on AIME 25 (Peak Accuracy) Source: [Mathematical Reasoning on AIME 25 (Peak Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-05-27T08:40:39.373Z Evaluation of model performance on the AIME 25 dataset for mathematical reasoning, specifically reporting the Peak Accuracy metric. 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 25 | | Metric | Peak Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Peak Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Peak Accuracy | Result date | Report paper | | --- | --- | --- | --- | | 14B-PC | 27.5 | Not recorded | 6a167a79dbd7150506f7fed0 | | 14B-GRPO | 23.6 | Not recorded | 6a167a79dbd7150506f7fed0 | | 14B-DAPO | 21.9 | Not recorded | 6a167a79dbd7150506f7fed0 | | 8B-PC | 21.4 | Not recorded | 6a167a79dbd7150506f7fed0 | | 8B-DAPO | 20.8 | Not recorded | 6a167a79dbd7150506f7fed0 | | 4B-PC | 19.6 | Not recorded | 6a167a79dbd7150506f7fed0 | | 4B-DAPO | 19.1 | Not recorded | 6a167a79dbd7150506f7fed0 | | 4B-GRPO | 17.4 | Not recorded | 6a167a79dbd7150506f7fed0 | | 8B-GRPO | 16.6 | Not recorded | 6a167a79dbd7150506f7fed0 | | 1.5B-PC | 15.3 | Not recorded | 6a167a79dbd7150506f7fed0 | | 1.5B-DAPO | 14.5 | Not recorded | 6a167a79dbd7150506f7fed0 | | 1.5B-GRPO | 14.3 | Not recorded | 6a167a79dbd7150506f7fed0 | ### 14B-PC Peak Accuracy: 27.5. Result ID: 6a16ace4fbc373592c0fd8d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"14B","RL Algorithm":"PC","Rollouts Trained":"2,048","Rollouts Sampled":"4,096"}. This record does not assert independent reproduction. ### 14B-GRPO Peak Accuracy: 23.6. Result ID: 6a16ace4fbc373592c0fd8d0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"14B","RL Algorithm":"GRPO","Rollouts Trained":"2,048","Rollouts Sampled":"2,048"}. This record does not assert independent reproduction. ### 14B-DAPO Peak Accuracy: 21.9. Result ID: 6a16ace4fbc373592c0fd8d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"14B","RL Algorithm":"DAPO","Rollouts Trained":"2,048","Rollouts Sampled":"6,144"}. This record does not assert independent reproduction. ### 8B-PC Peak Accuracy: 21.4. Result ID: 6a16ace4fbc373592c0fd8cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"8B","RL Algorithm":"PC","Rollouts Trained":"2,048","Rollouts Sampled":"4,096"}. This record does not assert independent reproduction. ### 8B-DAPO Peak Accuracy: 20.8. Result ID: 6a16ace4fbc373592c0fd8ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"8B","RL Algorithm":"DAPO","Rollouts Trained":"2,048","Rollouts Sampled":"6,144"}. This record does not assert independent reproduction. ### 4B-PC Peak Accuracy: 19.6. Result ID: 6a16ace4fbc373592c0fd8cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"4B","RL Algorithm":"PC","Rollouts Trained":"2,048","Rollouts Sampled":"4,096"}. This record does not assert independent reproduction. ### 4B-DAPO Peak Accuracy: 19.1. Result ID: 6a16ace4fbc373592c0fd8cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"4B","RL Algorithm":"DAPO","Rollouts Trained":"2,048","Rollouts Sampled":"6,144"}. This record does not assert independent reproduction. ### 4B-GRPO Peak Accuracy: 17.4. Result ID: 6a16ace4fbc373592c0fd8ca. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"4B","RL Algorithm":"GRPO","Rollouts Trained":"2,048","Rollouts Sampled":"2,048"}. This record does not assert independent reproduction. ### 8B-GRPO Peak Accuracy: 16.6. Result ID: 6a16ace4fbc373592c0fd8cd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"8B","RL Algorithm":"GRPO","Rollouts Trained":"2,048","Rollouts Sampled":"2,048"}. This record does not assert independent reproduction. ### 1.5B-PC Peak Accuracy: 15.3. Result ID: 6a16ace4fbc373592c0fd8c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"1.5B","RL Algorithm":"PC","Rollouts Trained":"2,048","Rollouts Sampled":"4,096"}. This record does not assert independent reproduction. ### 1.5B-DAPO Peak Accuracy: 14.5. Result ID: 6a16ace4fbc373592c0fd8c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"1.5B","RL Algorithm":"DAPO","Rollouts Trained":"2,048","Rollouts Sampled":"6,144"}. This record does not assert independent reproduction. ### 1.5B-GRPO Peak Accuracy: 14.3. Result ID: 6a16ace4fbc373592c0fd8c7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Scale":"1.5B","RL Algorithm":"GRPO","Rollouts Trained":"2,048","Rollouts Sampled":"2,048"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.