# Mathematical Reasoning on AIME 25 (Acc., Tokens) Source: [Mathematical Reasoning on AIME 25 (Acc., Tokens)]() Collection index: [llms.txt]() Data updated: 2026-05-15T09:52:02.961Z Evaluation of model performance on the AIME 25 dataset for mathematical reasoning, reporting standard accuracy and token usage metrics. 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 | Accuracy (AIME 25) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 25 of 25 | | 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 - [Accuracy (AIME 25)](): Higher is better; unit: PERCENT. - [Average Tokens](): Lower is better; unit: SCALAR. ## Recorded results | Method | Accuracy (AIME 25) | Result date | Report paper | | --- | --- | --- | --- | | D-L | 86.4 | Not recorded | 6a06a8c7dbc836b87d82a33f | | DDC | 83.3 | Not recorded | 6a06a8c7dbc836b87d82a33f | | SC | 82.3 | Not recorded | 6a06a8c7dbc836b87d82a33f | | AC | 82.3 | Not recorded | 6a06a8c7dbc836b87d82a33f | | DDC | 82.1 | Not recorded | 6a06a8c7dbc836b87d82a33f | | D-H | 81.4 | Not recorded | 6a06a8c7dbc836b87d82a33f | | D-L | 80.2 | Not recorded | 6a06a8c7dbc836b87d82a33f | | D-H | 80.2 | Not recorded | 6a06a8c7dbc836b87d82a33f | | SC | 80.1 | Not recorded | 6a06a8c7dbc836b87d82a33f | | AC | 80 | Not recorded | 6a06a8c7dbc836b87d82a33f | | DDC | 79.7 | Not recorded | 6a06a8c7dbc836b87d82a33f | | D-H | 78.5 | Not recorded | 6a06a8c7dbc836b87d82a33f | | SC | 78.1 | Not recorded | 6a06a8c7dbc836b87d82a33f | | D-L | 76.7 | Not recorded | 6a06a8c7dbc836b87d82a33f | | D-L | 73.3 | Not recorded | 6a06a8c7dbc836b87d82a33f | | DDC | 73.3 | Not recorded | 6a06a8c7dbc836b87d82a33f | | AC | 70 | Not recorded | 6a06a8c7dbc836b87d82a33f | | D-H | 66.7 | Not recorded | 6a06a8c7dbc836b87d82a33f | | SC | 66.5 | Not recorded | 6a06a8c7dbc836b87d82a33f | | AC | 66.4 | Not recorded | 6a06a8c7dbc836b87d82a33f | | D-L | 53.3 | Not recorded | 6a06a8c7dbc836b87d82a33f | | D-H | 53 | Not recorded | 6a06a8c7dbc836b87d82a33f | | DDC | 50 | Not recorded | 6a06a8c7dbc836b87d82a33f | | SC | 49.5 | Not recorded | 6a06a8c7dbc836b87d82a33f | | AC | 49.4 | Not recorded | 6a06a8c7dbc836b87d82a33f | ### D-L Accuracy (AIME 25): 86.4. Result ID: 6a06ecac47f34ce924ef0d82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-0528-Qwen3-8B","Voting size budget":"512"}. This record does not assert independent reproduction. ### DDC Accuracy (AIME 25): 83.3. Result ID: 6a06ecac47f34ce924ef0d84. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-0528-Qwen3-8B","Voting size budget":"512"}. This record does not assert independent reproduction. ### SC Accuracy (AIME 25): 82.3. Result ID: 6a06ecac47f34ce924ef0d80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-0528-Qwen3-8B","Voting size budget":"512"}. This record does not assert independent reproduction. ### AC Accuracy (AIME 25): 82.3. Result ID: 6a06ecac47f34ce924ef0d81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-0528-Qwen3-8B","Voting size budget":"512"}. This record does not assert independent reproduction. ### DDC Accuracy (AIME 25): 82.1. Result ID: 6a06ecac47f34ce924ef0d75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Voting size budget":"512"}. This record does not assert independent reproduction. ### D-H Accuracy (AIME 25): 81.4. Result ID: 6a06ecac47f34ce924ef0d83. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-0528-Qwen3-8B","Voting size budget":"512"}. This record does not assert independent reproduction. ### D-L Accuracy (AIME 25): 80.2. Result ID: 6a06ecac47f34ce924ef0d7d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-32B","Voting size budget":"512"}. This record does not assert independent reproduction. ### D-H Accuracy (AIME 25): 80.2. Result ID: 6a06ecac47f34ce924ef0d7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-32B","Voting size budget":"512"}. This record does not assert independent reproduction. ### SC Accuracy (AIME 25): 80.1. Result ID: 6a06ecac47f34ce924ef0d7b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-32B","Voting size budget":"512"}. This record does not assert independent reproduction. ### AC Accuracy (AIME 25): 80. Result ID: 6a06ecac47f34ce924ef0d7c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-32B","Voting size budget":"512"}. This record does not assert independent reproduction. ### DDC Accuracy (AIME 25): 79.7. Result ID: 6a06ecac47f34ce924ef0d7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-32B","Voting size budget":"512"}. This record does not assert independent reproduction. ### D-H Accuracy (AIME 25): 78.5. Result ID: 6a06ecac47f34ce924ef0d79. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Voting size budget":"512"}. This record does not assert independent reproduction. ### SC Accuracy (AIME 25): 78.1. Result ID: 6a06ecac47f34ce924ef0d76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Voting size budget":"512"}. This record does not assert independent reproduction. ### D-L Accuracy (AIME 25): 76.7. Result ID: 6a06ecac47f34ce924ef0d78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Voting size budget":"512"}. This record does not assert independent reproduction. ### D-L Accuracy (AIME 25): 73.3. Result ID: 6a06ecac47f34ce924ef0d73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Voting size budget":"512"}. This record does not assert independent reproduction. ### DDC Accuracy (AIME 25): 73.3. Result ID: 6a06ecac47f34ce924ef0d7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Voting size budget":"512"}. This record does not assert independent reproduction. ### AC Accuracy (AIME 25): 70. Result ID: 6a06ecac47f34ce924ef0d77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Voting size budget":"512"}. This record does not assert independent reproduction. ### D-H Accuracy (AIME 25): 66.7. Result ID: 6a06ecac47f34ce924ef0d74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Voting size budget":"512"}. This record does not assert independent reproduction. ### SC Accuracy (AIME 25): 66.5. Result ID: 6a06ecac47f34ce924ef0d71. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Voting size budget":"512"}. This record does not assert independent reproduction. ### AC Accuracy (AIME 25): 66.4. Result ID: 6a06ecac47f34ce924ef0d72. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Voting size budget":"512"}. This record does not assert independent reproduction. ### D-L Accuracy (AIME 25): 53.3. Result ID: 6a06ecac47f34ce924ef0d6e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Voting size budget":"512"}. This record does not assert independent reproduction. ### D-H Accuracy (AIME 25): 53. Result ID: 6a06ecac47f34ce924ef0d6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Voting size budget":"512"}. This record does not assert independent reproduction. ### DDC Accuracy (AIME 25): 50. Result ID: 6a06ecac47f34ce924ef0d70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Voting size budget":"512"}. This record does not assert independent reproduction. ### SC Accuracy (AIME 25): 49.5. Result ID: 6a06ecac47f34ce924ef0d6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Voting size budget":"512"}. This record does not assert independent reproduction. ### AC Accuracy (AIME 25): 49.4. Result ID: 6a06ecac47f34ce924ef0d6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Voting size budget":"512"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.