# Mathematical Reasoning on Minerva Math (Peak Accuracy) Source: [Mathematical Reasoning on Minerva Math (Peak Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-05-27T08:40:39.405Z Evaluation of model performance on complex mathematical reasoning problems using the Minerva Math dataset, specifically reporting the Peak Accuracy score. 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) | Minerva Math | | 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 | 39.3 | Not recorded | 6a167a79dbd7150506f7fed0 | | 8B-PC | 39 | Not recorded | 6a167a79dbd7150506f7fed0 | | 14B-GRPO | 38.6 | Not recorded | 6a167a79dbd7150506f7fed0 | | 8B-GRPO | 38.2 | Not recorded | 6a167a79dbd7150506f7fed0 | | 14B-DAPO | 38.2 | Not recorded | 6a167a79dbd7150506f7fed0 | | 8B-DAPO | 37.5 | Not recorded | 6a167a79dbd7150506f7fed0 | | 4B-PC | 36.8 | Not recorded | 6a167a79dbd7150506f7fed0 | | 4B-GRPO | 35.3 | Not recorded | 6a167a79dbd7150506f7fed0 | | 4B-DAPO | 34.6 | Not recorded | 6a167a79dbd7150506f7fed0 | | 1.5B-DAPO | 29.4 | Not recorded | 6a167a79dbd7150506f7fed0 | | 1.5B-GRPO | 28.7 | Not recorded | 6a167a79dbd7150506f7fed0 | | 1.5B-PC | 28.7 | Not recorded | 6a167a79dbd7150506f7fed0 | ### 14B-PC Peak Accuracy: 39.3. Result ID: 6a16ace4fbc373592c0fd8ea. [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. ### 8B-PC Peak Accuracy: 39. Result ID: 6a16ace4fbc373592c0fd8e7. [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. ### 14B-GRPO Peak Accuracy: 38.6. Result ID: 6a16ace4fbc373592c0fd8e8. [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. ### 8B-GRPO Peak Accuracy: 38.2. Result ID: 6a16ace4fbc373592c0fd8e5. [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. ### 14B-DAPO Peak Accuracy: 38.2. Result ID: 6a16ace4fbc373592c0fd8e9. [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-DAPO Peak Accuracy: 37.5. Result ID: 6a16ace4fbc373592c0fd8e6. [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: 36.8. Result ID: 6a16ace4fbc373592c0fd8e4. [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-GRPO Peak Accuracy: 35.3. Result ID: 6a16ace4fbc373592c0fd8e2. [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. ### 4B-DAPO Peak Accuracy: 34.6. Result ID: 6a16ace4fbc373592c0fd8e3. [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. ### 1.5B-DAPO Peak Accuracy: 29.4. Result ID: 6a16ace4fbc373592c0fd8e0. [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: 28.7. Result ID: 6a16ace4fbc373592c0fd8df. [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. ### 1.5B-PC Peak Accuracy: 28.7. Result ID: 6a16ace4fbc373592c0fd8e1. [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. Page 1 of 1. This is an index page, not the full collection.