# Mathematical Problem Solving on MATH (Best-of-N accuracy) Source: [Mathematical Problem Solving on MATH (Best-of-N accuracy)]() Collection index: [llms.txt]() Data updated: 2026-03-05T07:28:40.991Z Evaluation of model performance on the MATH dataset for mathematical problem-solving tasks, specifically measured using the Best-of-N accuracy metric. 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 Problem Solving | | Dataset (including any stated split) | MATH | | Metric | Best-of-N 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 - [Best-of-N Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Best-of-N Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MSV 64 | 76.07 | Not recorded | 69a90de32d603e6de3e40602 | | Probe + WV | 75 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 16 | 74.72 | Not recorded | 69a90de32d603e6de3e40602 | | Probe + WV | 74.5 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 1 + WV | 74.42 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 1 + WV | 74.4 | Not recorded | 69a90de32d603e6de3e40602 | | Probe | 74.29 | Not recorded | 69a90de32d603e6de3e40602 | | Probe | 73.45 | Not recorded | 69a90de32d603e6de3e40602 | | Probe + WV | 72.5 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 1 | 72.46 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 1 | 72.38 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 1 + WV | 72.24 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 4 | 72.19 | Not recorded | 69a90de32d603e6de3e40602 | | Probe | 71.97 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 1 | 71.55 | Not recorded | 69a90de32d603e6de3e40602 | | Probe | 67.55 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 1 | 67.55 | Not recorded | 69a90de32d603e6de3e40602 | ### MSV 64 Best-of-N Accuracy: 76.07. Result ID: 69a9309b6dbb7075b95233ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"64"}. This record does not assert independent reproduction. ### Probe + WV Best-of-N Accuracy: 75. Result ID: 69a9309b6dbb7075b95233a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"64"}. This record does not assert independent reproduction. ### MSV 16 Best-of-N Accuracy: 74.72. Result ID: 69a9309b6dbb7075b95233a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"16"}. This record does not assert independent reproduction. ### Probe + WV Best-of-N Accuracy: 74.5. Result ID: 69a9309b6dbb7075b95233a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"16"}. This record does not assert independent reproduction. ### MSV 1 + WV Best-of-N Accuracy: 74.42. Result ID: 69a9309b6dbb7075b95233aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"64"}. This record does not assert independent reproduction. ### MSV 1 + WV Best-of-N Accuracy: 74.4. Result ID: 69a9309b6dbb7075b95233a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"16"}. This record does not assert independent reproduction. ### Probe Best-of-N Accuracy: 74.29. Result ID: 69a9309b6dbb7075b95233a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"64"}. This record does not assert independent reproduction. ### Probe Best-of-N Accuracy: 73.45. Result ID: 69a9309b6dbb7075b95233a2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"16"}. This record does not assert independent reproduction. ### Probe + WV Best-of-N Accuracy: 72.5. Result ID: 69a9309b6dbb7075b952339f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"4"}. This record does not assert independent reproduction. ### MSV 1 Best-of-N Accuracy: 72.46. Result ID: 69a9309b6dbb7075b95233a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"64"}. This record does not assert independent reproduction. ### MSV 1 Best-of-N Accuracy: 72.38. Result ID: 69a9309b6dbb7075b95233a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"16"}. This record does not assert independent reproduction. ### MSV 1 + WV Best-of-N Accuracy: 72.24. Result ID: 69a9309b6dbb7075b95233a0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"4"}. This record does not assert independent reproduction. ### MSV 4 Best-of-N Accuracy: 72.19. Result ID: 69a9309b6dbb7075b95233a1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"4"}. This record does not assert independent reproduction. ### Probe Best-of-N Accuracy: 71.97. Result ID: 69a9309b6dbb7075b952339d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"4"}. This record does not assert independent reproduction. ### MSV 1 Best-of-N Accuracy: 71.55. Result ID: 69a9309b6dbb7075b952339e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"4"}. This record does not assert independent reproduction. ### Probe Best-of-N Accuracy: 67.55. Result ID: 69a9309b6dbb7075b952339b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"1"}. This record does not assert independent reproduction. ### MSV 1 Best-of-N Accuracy: 67.55. Result ID: 69a9309b6dbb7075b952339c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.