# Mathematical Reasoning on AIME Think (test) Source: [Mathematical Reasoning on AIME Think (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:31:02.771Z Evaluation of model performance on the AIME Think test set, reporting Accuracy, output Length, and Wait time. 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 Think (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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](): Higher is better; unit: PERCENT. - [Output Length](): Higher is better; unit: SCALAR. - [Wait Time](): Lower is better; unit: TIME. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Qwen3-8B | 72.4 | Not recorded | 6965d1ae6343fa78c8323884 | | Qwen3-8B | 72 | Not recorded | 6965d1ae6343fa78c8323884 | | Qwen3-8B | 71.6 | Not recorded | 6965d1ae6343fa78c8323884 | | Qwen3-8B | 69.8 | Not recorded | 6965d1ae6343fa78c8323884 | | Qwen3-4B | 69.6 | Not recorded | 6965d1ae6343fa78c8323884 | | Qwen3-4B | 69.3 | Not recorded | 6965d1ae6343fa78c8323884 | | Qwen3-4B | 68.7 | Not recorded | 6965d1ae6343fa78c8323884 | | Qwen3-4B | 61.1 | Not recorded | 6965d1ae6343fa78c8323884 | ### Qwen3-8B Accuracy: 72.4. Result ID: 69968f565698665ec4d83c29. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training":"RL","Mode":"Mid-Think"}. This record does not assert independent reproduction. ### Qwen3-8B Accuracy: 72. Result ID: 69968f565698665ec4d83c28. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training":"RL","Mode":"No-Think"}. This record does not assert independent reproduction. ### Qwen3-8B Accuracy: 71.6. Result ID: 69968f565698665ec4d83c26. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training":"No","Mode":"Untrained"}. This record does not assert independent reproduction. ### Qwen3-8B Accuracy: 69.8. Result ID: 69968f565698665ec4d83c27. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training":"RL","Mode":"Think"}. This record does not assert independent reproduction. ### Qwen3-4B Accuracy: 69.6. Result ID: 69968f565698665ec4d83c2d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training":"RL","Mode":"Mid-Think"}. This record does not assert independent reproduction. ### Qwen3-4B Accuracy: 69.3. Result ID: 69968f565698665ec4d83c2c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training":"RL","Mode":"No-Think"}. This record does not assert independent reproduction. ### Qwen3-4B Accuracy: 68.7. Result ID: 69968f565698665ec4d83c2a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training":"No","Mode":"Untrained"}. This record does not assert independent reproduction. ### Qwen3-4B Accuracy: 61.1. Result ID: 69968f565698665ec4d83c2b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training":"RL","Mode":"Think"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.