# Mathematical Reasoning on AIME 2024 (Accuracy, Avg Acc, Avg TPF) Source: [Mathematical Reasoning on AIME 2024 (Accuracy, Avg Acc, Avg TPF)]() Collection index: [llms.txt]() Data updated: 2026-07-08T07:04:52.872Z Evaluation of model performance on the American Invitational Mathematics Examination (AIME) 2024 dataset, reporting Accuracy, Average Accuracy (Avg Acc), and Average True Positive Factor (Avg TPF). 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 2024 | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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. - [Average Accuracy](): Higher is better; unit: PERCENT. - [Average TPF](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Nemotron-Labs-Diffusion-14B | 53.33 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Nemotron-Labs-Diffusion-14B | 50 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Nemotron-Labs-Diffusion-14B | 46.67 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Nemotron-Labs-Diffusion-14B | 43.33 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Ministral3-14B-Instruct-2512 | 36.25 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Qwen3-14B | 33.33 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Nemotron-Labs-Diffusion-3B | 26.67 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Gemma-3-12B-IT | 23.75 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Nemotron-Labs-Diffusion-3B | 23.33 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Phi-4-14B | 19.17 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Nemotron-Labs-Diffusion-3B | 16.67 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Nemotron-Labs-Diffusion-3B | 13.33 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Ministral3-3B-Instruct-2512 | 12.5 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Qwen3-4B | 10.63 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Phi-4-mini-Instruct | 10 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Phi-3-Medium-14B | 1.88 | Not recorded | 6a4dd9b44da6617fe9198c51 | | Llama-3.2-3B-Instruct | 0 | Not recorded | 6a4dd9b44da6617fe9198c51 | ### Nemotron-Labs-Diffusion-14B Accuracy: 53.33. Result ID: 6a4df68960b88bb339d6b9ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"14B","Gen. Mode":"Quad. SS"}. This record does not assert independent reproduction. ### Nemotron-Labs-Diffusion-14B Accuracy: 50. Result ID: 6a4df68960b88bb339d6b9ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"14B","Gen. Mode":"Linear SS"}. This record does not assert independent reproduction. ### Nemotron-Labs-Diffusion-14B Accuracy: 46.67. Result ID: 6a4df68960b88bb339d6b9ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"14B","Gen. Mode":"AR"}. This record does not assert independent reproduction. ### Nemotron-Labs-Diffusion-14B Accuracy: 43.33. Result ID: 6a4df68960b88bb339d6b9ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"14B","Gen. Mode":"Diff."}. This record does not assert independent reproduction. ### Ministral3-14B-Instruct-2512 Accuracy: 36.25. Result ID: 6a4df68960b88bb339d6b9a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"14B","Gen. Mode":"AR"}. This record does not assert independent reproduction. ### Qwen3-14B Accuracy: 33.33. Result ID: 6a4df68960b88bb339d6b9aa. [Reporting paper]() Recorded evaluation configuration: {"Scale":"14B","Gen. Mode":"AR"}. This record does not assert independent reproduction. ### Nemotron-Labs-Diffusion-3B Accuracy: 26.67. Result ID: 6a4df68960b88bb339d6b9a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"3B","Gen. Mode":"Linear SS"}. This record does not assert independent reproduction. ### Gemma-3-12B-IT Accuracy: 23.75. Result ID: 6a4df68960b88bb339d6b9a6. [Reporting paper]() Recorded evaluation configuration: {"Scale":"14B","Gen. Mode":"AR"}. This record does not assert independent reproduction. ### Nemotron-Labs-Diffusion-3B Accuracy: 23.33. Result ID: 6a4df68960b88bb339d6b9a2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"3B","Gen. Mode":"AR"}. This record does not assert independent reproduction. ### Phi-4-14B Accuracy: 19.17. Result ID: 6a4df68960b88bb339d6b9a8. [Reporting paper]() Recorded evaluation configuration: {"Scale":"14B","Gen. Mode":"AR"}. This record does not assert independent reproduction. ### Nemotron-Labs-Diffusion-3B Accuracy: 16.67. Result ID: 6a4df68960b88bb339d6b9a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"3B","Gen. Mode":"Diff."}. This record does not assert independent reproduction. ### Nemotron-Labs-Diffusion-3B Accuracy: 13.33. Result ID: 6a4df68960b88bb339d6b9a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"3B","Gen. Mode":"Quad. SS"}. This record does not assert independent reproduction. ### Ministral3-3B-Instruct-2512 Accuracy: 12.5. Result ID: 6a4df68960b88bb339d6b9a0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Scale":"3B","Gen. Mode":"AR"}. This record does not assert independent reproduction. ### Qwen3-4B Accuracy: 10.63. Result ID: 6a4df68960b88bb339d6b9a1. [Reporting paper]() Recorded evaluation configuration: {"Scale":"3B","Gen. Mode":"AR"}. This record does not assert independent reproduction. ### Phi-4-mini-Instruct Accuracy: 10. Result ID: 6a4df68960b88bb339d6b99f. [Reporting paper]() Recorded evaluation configuration: {"Scale":"3B","Gen. Mode":"AR"}. This record does not assert independent reproduction. ### Phi-3-Medium-14B Accuracy: 1.88. Result ID: 6a4df68960b88bb339d6b9a7. [Reporting paper]() Recorded evaluation configuration: {"Scale":"14B","Gen. Mode":"AR"}. This record does not assert independent reproduction. ### Llama-3.2-3B-Instruct Accuracy: 0. Result ID: 6a4df68960b88bb339d6b99e. [Reporting paper]() Recorded evaluation configuration: {"Scale":"3B","Gen. Mode":"AR"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.