# Mathematical Reasoning on AIME 2024 (Accuracy, Gen. Cost) Source: [Mathematical Reasoning on AIME 2024 (Accuracy, Gen. Cost)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:34.427Z Evaluation of model performance on the American Invitational Mathematics Examination (AIME) 2024 dataset, reporting Accuracy and Generation Cost. 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 | 18 of 18 | | 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. - [Generation Cost](): Lower is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | ZIP-RC sampling | 65.8 | Not recorded | 692e7312d6b0dd3342932727 | | ZIP-RC sampling | 60.9 | Not recorded | 692e7312d6b0dd3342932727 | | Weighted BoN Self-eval | 59.4 | Not recorded | 692e7312d6b0dd3342932727 | | ZIP-RC reward prune | 57.5 | Not recorded | 692e7312d6b0dd3342932727 | | Weighted BoN Self-eval | 55.1 | Not recorded | 692e7312d6b0dd3342932727 | | Weighted BoN ext. RM | 54.7 | Not recorded | 692e7312d6b0dd3342932727 | | Majority Voting | 53.1 | Not recorded | 692e7312d6b0dd3342932727 | | MV length-prune | 51.3 | Not recorded | 692e7312d6b0dd3342932727 | | Weighted BoN ext. RM | 50.3 | Not recorded | 692e7312d6b0dd3342932727 | | Majority Voting | 49.6 | Not recorded | 692e7312d6b0dd3342932727 | | ZIP-RC reward prune | 43.3 | Not recorded | 692e7312d6b0dd3342932727 | | ZIP-RC sampling | 38.8 | Not recorded | 692e7312d6b0dd3342932727 | | Weighted BoN Self-eval | 31.4 | Not recorded | 692e7312d6b0dd3342932727 | | Weighted BoN ext. RM | 28.5 | Not recorded | 692e7312d6b0dd3342932727 | | MV length-prune | 28.3 | Not recorded | 692e7312d6b0dd3342932727 | | Majority Voting | 26.9 | Not recorded | 692e7312d6b0dd3342932727 | | MV length-prune | 25.1 | Not recorded | 692e7312d6b0dd3342932727 | | ZIP-RC reward prune | 21.7 | Not recorded | 692e7312d6b0dd3342932727 | ### ZIP-RC sampling Accuracy: 65.8. Result ID: 699997355698665ec40b460a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B"}. This record does not assert independent reproduction. ### ZIP-RC sampling Accuracy: 60.9. Result ID: 699997355698665ec40b4610. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-1.2B"}. This record does not assert independent reproduction. ### Weighted BoN Self-eval Accuracy: 59.4. Result ID: 699997355698665ec40b460e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B"}. This record does not assert independent reproduction. ### ZIP-RC reward prune Accuracy: 57.5. Result ID: 699997355698665ec40b4615. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-1.2B"}. This record does not assert independent reproduction. ### Weighted BoN Self-eval Accuracy: 55.1. Result ID: 699997355698665ec40b4614. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-1.2B"}. This record does not assert independent reproduction. ### Weighted BoN ext. RM Accuracy: 54.7. Result ID: 699997355698665ec40b460d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B"}. This record does not assert independent reproduction. ### Majority Voting Accuracy: 53.1. Result ID: 699997355698665ec40b460b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B"}. This record does not assert independent reproduction. ### MV length-prune Accuracy: 51.3. Result ID: 699997355698665ec40b4612. [Reporting paper]() Recorded evaluation configuration: {"Model":"LFM2-1.2B"}. This record does not assert independent reproduction. ### Weighted BoN ext. RM Accuracy: 50.3. Result ID: 699997355698665ec40b4613. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"LFM2-1.2B"}. This record does not assert independent reproduction. ### Majority Voting Accuracy: 49.6. Result ID: 699997355698665ec40b4611. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-1.2B"}. This record does not assert independent reproduction. ### ZIP-RC reward prune Accuracy: 43.3. Result ID: 699997355698665ec40b460f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B"}. This record does not assert independent reproduction. ### ZIP-RC sampling Accuracy: 38.8. Result ID: 699997355698665ec40b4616. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-350M"}. This record does not assert independent reproduction. ### Weighted BoN Self-eval Accuracy: 31.4. Result ID: 699997355698665ec40b461a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-350M"}. This record does not assert independent reproduction. ### Weighted BoN ext. RM Accuracy: 28.5. Result ID: 699997355698665ec40b4619. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"LFM2-350M"}. This record does not assert independent reproduction. ### MV length-prune Accuracy: 28.3. Result ID: 699997355698665ec40b4618. [Reporting paper]() Recorded evaluation configuration: {"Model":"LFM2-350M"}. This record does not assert independent reproduction. ### Majority Voting Accuracy: 26.9. Result ID: 699997355698665ec40b4617. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-350M"}. This record does not assert independent reproduction. ### MV length-prune Accuracy: 25.1. Result ID: 699997355698665ec40b460c. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B"}. This record does not assert independent reproduction. ### ZIP-RC reward prune Accuracy: 21.7. Result ID: 699997355698665ec40b461b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-350M"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.