# Numerical Generation on NUPA Source: [Numerical Generation on NUPA]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:42:28.241Z Evaluation of model performance on numerical generation tasks using the NUPA dataset, measured primarily by Exact Match accuracy. 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 | Numerical Generation | | Dataset (including any stated split) | NUPA | | Metric | Exact Match | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 28 of 28 | | 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 - [Exact Match](): Higher is better; unit: PERCENT. ## Recorded results | Method | Exact Match | Result date | Report paper | | --- | --- | --- | --- | | Numerologic | 83.7 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-MLP | 83.3 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-RNN | 81.4 | Not recorded | 69687483e25ad2fa9d1ec536 | | Numerologic | 78 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-MLP | 77.6 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-RNN | 77.6 | Not recorded | 69687483e25ad2fa9d1ec536 | | Standard Transformer | 73.3 | Not recorded | 69687483e25ad2fa9d1ec536 | | Standard Transformer | 71.9 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-RNN | 68.9 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-MLP | 68.4 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-MLP | 68.1 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-RNN | 67.7 | Not recorded | 69687483e25ad2fa9d1ec536 | | Numerologic | 67.5 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-RNN | 66.3 | Not recorded | 69687483e25ad2fa9d1ec536 | | Standard Transformer | 65.7 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-MLP | 65.6 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-RNN | 65.3 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-MLP | 64.7 | Not recorded | 69687483e25ad2fa9d1ec536 | | Standard Transformer | 64.6 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-RNN | 64.2 | Not recorded | 69687483e25ad2fa9d1ec536 | | NumValue-MLP | 63.8 | Not recorded | 69687483e25ad2fa9d1ec536 | | Standard Transformer | 61.9 | Not recorded | 69687483e25ad2fa9d1ec536 | | Standard Transformer | 61.3 | Not recorded | 69687483e25ad2fa9d1ec536 | | Numerologic | 61 | Not recorded | 69687483e25ad2fa9d1ec536 | | Standard Transformer | 60.4 | Not recorded | 69687483e25ad2fa9d1ec536 | | Numerologic | 59.9 | Not recorded | 69687483e25ad2fa9d1ec536 | | Numerologic | 57.1 | Not recorded | 69687483e25ad2fa9d1ec536 | | Numerologic | 55.6 | Not recorded | 69687483e25ad2fa9d1ec536 | ### Numerologic Exact Match: 83.7. Result ID: 699684375698665ec4cc6f3e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"1"}. This record does not assert independent reproduction. ### NumValue-MLP Exact Match: 83.3. Result ID: 699684375698665ec4cc6f3f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"1"}. This record does not assert independent reproduction. ### NumValue-RNN Exact Match: 81.4. Result ID: 699684375698665ec4cc6f40. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"1"}. This record does not assert independent reproduction. ### Numerologic Exact Match: 78. Result ID: 699684375698665ec4cc6f42. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"2"}. This record does not assert independent reproduction. ### NumValue-MLP Exact Match: 77.6. Result ID: 699684375698665ec4cc6f47. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"3"}. This record does not assert independent reproduction. ### NumValue-RNN Exact Match: 77.6. Result ID: 699684375698665ec4cc6f48. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"3"}. This record does not assert independent reproduction. ### Standard Transformer Exact Match: 73.3. Result ID: 699684375698665ec4cc6f45. [Reporting paper]() Recorded evaluation configuration: {"# Digits":"3"}. This record does not assert independent reproduction. ### Standard Transformer Exact Match: 71.9. Result ID: 699684375698665ec4cc6f3d. [Reporting paper]() Recorded evaluation configuration: {"# Digits":"1"}. This record does not assert independent reproduction. ### NumValue-RNN Exact Match: 68.9. Result ID: 699684375698665ec4cc6f50. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"5"}. This record does not assert independent reproduction. ### NumValue-MLP Exact Match: 68.4. Result ID: 699684375698665ec4cc6f43. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"2"}. This record does not assert independent reproduction. ### NumValue-MLP Exact Match: 68.1. Result ID: 699684375698665ec4cc6f4f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"5"}. This record does not assert independent reproduction. ### NumValue-RNN Exact Match: 67.7. Result ID: 699684375698665ec4cc6f44. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"2"}. This record does not assert independent reproduction. ### Numerologic Exact Match: 67.5. Result ID: 699684375698665ec4cc6f46. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"3"}. This record does not assert independent reproduction. ### NumValue-RNN Exact Match: 66.3. Result ID: 699684375698665ec4cc6f4c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"4"}. This record does not assert independent reproduction. ### Standard Transformer Exact Match: 65.7. Result ID: 699684375698665ec4cc6f41. [Reporting paper]() Recorded evaluation configuration: {"# Digits":"2"}. This record does not assert independent reproduction. ### NumValue-MLP Exact Match: 65.6. Result ID: 699684375698665ec4cc6f4b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"4"}. This record does not assert independent reproduction. ### NumValue-RNN Exact Match: 65.3. Result ID: 699684375698665ec4cc6f54. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"6"}. This record does not assert independent reproduction. ### NumValue-MLP Exact Match: 64.7. Result ID: 699684375698665ec4cc6f53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"6"}. This record does not assert independent reproduction. ### Standard Transformer Exact Match: 64.6. Result ID: 699684375698665ec4cc6f4d. [Reporting paper]() Recorded evaluation configuration: {"# Digits":"5"}. This record does not assert independent reproduction. ### NumValue-RNN Exact Match: 64.2. Result ID: 699684375698665ec4cc6f58. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"7"}. This record does not assert independent reproduction. ### NumValue-MLP Exact Match: 63.8. Result ID: 699684375698665ec4cc6f57. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"7"}. This record does not assert independent reproduction. ### Standard Transformer Exact Match: 61.9. Result ID: 699684375698665ec4cc6f51. [Reporting paper]() Recorded evaluation configuration: {"# Digits":"6"}. This record does not assert independent reproduction. ### Standard Transformer Exact Match: 61.3. Result ID: 699684375698665ec4cc6f55. [Reporting paper]() Recorded evaluation configuration: {"# Digits":"7"}. This record does not assert independent reproduction. ### Numerologic Exact Match: 61. Result ID: 699684375698665ec4cc6f4a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"4"}. This record does not assert independent reproduction. ### Standard Transformer Exact Match: 60.4. Result ID: 699684375698665ec4cc6f49. [Reporting paper]() Recorded evaluation configuration: {"# Digits":"4"}. This record does not assert independent reproduction. ### Numerologic Exact Match: 59.9. Result ID: 699684375698665ec4cc6f4e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"5"}. This record does not assert independent reproduction. ### Numerologic Exact Match: 57.1. Result ID: 699684375698665ec4cc6f52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"6"}. This record does not assert independent reproduction. ### Numerologic Exact Match: 55.6. Result ID: 699684375698665ec4cc6f56. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"# Digits":"7"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.