# Mathematical Reasoning on AMC 2023 (Accuracy and Gen. Cost) Source: [Mathematical Reasoning on AMC 2023 (Accuracy and Gen. Cost)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:34.446Z Evaluation of model performance on the AMC 2023 dataset for Mathematical Reasoning, focusing on 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) | AMC 2023 | | 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 | 93.5 | Not recorded | 692e7312d6b0dd3342932727 | | Weighted BoN Self-eval | 91.8 | Not recorded | 692e7312d6b0dd3342932727 | | ZIP-RC sampling | 90.9 | Not recorded | 692e7312d6b0dd3342932727 | | Majority Voting | 90.6 | Not recorded | 692e7312d6b0dd3342932727 | | ZIP-RC reward prune | 90.2 | Not recorded | 692e7312d6b0dd3342932727 | | MV length-prune | 89.8 | Not recorded | 692e7312d6b0dd3342932727 | | Weighted BoN Self-eval | 89.1 | Not recorded | 692e7312d6b0dd3342932727 | | Weighted BoN ext. RM | 89 | Not recorded | 692e7312d6b0dd3342932727 | | Majority Voting | 87.9 | Not recorded | 692e7312d6b0dd3342932727 | | Weighted BoN ext. RM | 86.5 | Not recorded | 692e7312d6b0dd3342932727 | | ZIP-RC reward prune | 86 | Not recorded | 692e7312d6b0dd3342932727 | | ZIP-RC sampling | 83.9 | Not recorded | 692e7312d6b0dd3342932727 | | Weighted BoN Self-eval | 77.6 | Not recorded | 692e7312d6b0dd3342932727 | | MV length-prune | 74.8 | Not recorded | 692e7312d6b0dd3342932727 | | Majority Voting | 74.5 | Not recorded | 692e7312d6b0dd3342932727 | | Weighted BoN ext. RM | 73.4 | Not recorded | 692e7312d6b0dd3342932727 | | ZIP-RC reward prune | 69.7 | Not recorded | 692e7312d6b0dd3342932727 | | MV length-prune | 58.5 | Not recorded | 692e7312d6b0dd3342932727 | ### ZIP-RC sampling Accuracy: 93.5. Result ID: 699997355698665ec40b4622. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-1.2B"}. This record does not assert independent reproduction. ### Weighted BoN Self-eval Accuracy: 91.8. Result ID: 699997355698665ec40b4626. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-1.2B"}. This record does not assert independent reproduction. ### ZIP-RC sampling Accuracy: 90.9. Result ID: 699997355698665ec40b461c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B"}. This record does not assert independent reproduction. ### Majority Voting Accuracy: 90.6. Result ID: 699997355698665ec40b4623. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-1.2B"}. This record does not assert independent reproduction. ### ZIP-RC reward prune Accuracy: 90.2. Result ID: 699997355698665ec40b4627. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-1.2B"}. This record does not assert independent reproduction. ### MV length-prune Accuracy: 89.8. Result ID: 699997355698665ec40b4624. [Reporting paper]() Recorded evaluation configuration: {"Model":"LFM2-1.2B"}. This record does not assert independent reproduction. ### Weighted BoN Self-eval Accuracy: 89.1. Result ID: 699997355698665ec40b4620. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B"}. This record does not assert independent reproduction. ### Weighted BoN ext. RM Accuracy: 89. Result ID: 699997355698665ec40b4625. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"LFM2-1.2B"}. This record does not assert independent reproduction. ### Majority Voting Accuracy: 87.9. Result ID: 699997355698665ec40b461d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B"}. This record does not assert independent reproduction. ### Weighted BoN ext. RM Accuracy: 86.5. Result ID: 699997355698665ec40b461f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B"}. This record does not assert independent reproduction. ### ZIP-RC reward prune Accuracy: 86. Result ID: 699997355698665ec40b4621. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B"}. This record does not assert independent reproduction. ### ZIP-RC sampling Accuracy: 83.9. Result ID: 699997355698665ec40b4628. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-350M"}. This record does not assert independent reproduction. ### Weighted BoN Self-eval Accuracy: 77.6. Result ID: 699997355698665ec40b462c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-350M"}. This record does not assert independent reproduction. ### MV length-prune Accuracy: 74.8. Result ID: 699997355698665ec40b462a. [Reporting paper]() Recorded evaluation configuration: {"Model":"LFM2-350M"}. This record does not assert independent reproduction. ### Majority Voting Accuracy: 74.5. Result ID: 699997355698665ec40b4629. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-350M"}. This record does not assert independent reproduction. ### Weighted BoN ext. RM Accuracy: 73.4. Result ID: 699997355698665ec40b462b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"LFM2-350M"}. This record does not assert independent reproduction. ### ZIP-RC reward prune Accuracy: 69.7. Result ID: 699997355698665ec40b462d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"LFM2-350M"}. This record does not assert independent reproduction. ### MV length-prune Accuracy: 58.5. Result ID: 699997355698665ec40b461e. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-1.7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.