# Mathematical Reasoning on LiveMathBench 202505 Source: [Mathematical Reasoning on LiveMathBench 202505]() Collection index: [llms.txt]() Data updated: 2026-03-04T20:57:11.387Z Evaluation of model performance on the LiveMathBench 202505 dataset for mathematical reasoning, reporting accuracy, token usage, and efficiency. 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) | LiveMathBench 202505 | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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. - [Token Count](): Lower is better; unit: SCALAR. - [Efficiency Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Original | 32.17 | Not recorded | 69a66bcb2d603e6de3e3cb9e | | D-SFT-\>D-RL3k-\>D-RL6k | 31.83 | Not recorded | 69a66bcb2d603e6de3e3cb9e | | D-SFT-\>D-RL6k | 31.33 | Not recorded | 69a66bcb2d603e6de3e3cb9e | | D-SFT-\>D-RL3k-\>D-RL6k | 30.83 | Not recorded | 69a66bcb2d603e6de3e3cb9e | | D-SFT-\>D-RL6k | 30.67 | Not recorded | 69a66bcb2d603e6de3e3cb9e | | ThinkPrune(6k) | 28.67 | Not recorded | 69a66bcb2d603e6de3e3cb9e | | ThinkPrune(6k-\>3k) | 28.67 | Not recorded | 69a66bcb2d603e6de3e3cb9e | | D-SFT-\>D-RL6k | 26.33 | Not recorded | 69a66bcb2d603e6de3e3cb9e | | D-SFT-\>D-RL3k | 22.33 | Not recorded | 69a66bcb2d603e6de3e3cb9e | | D-SFT-\>D-RL3k-\>D-RL6k | 22.33 | Not recorded | 69a66bcb2d603e6de3e3cb9e | | D-SFT | 12.5 | Not recorded | 69a66bcb2d603e6de3e3cb9e | ### Original Accuracy: 32.17. Result ID: 69a89bbd6dbb7075b9517f4f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"step","Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### D-SFT-\>D-RL3k-\>D-RL6k Accuracy: 31.83. Result ID: 69a89bbd6dbb7075b9517f54. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"adaptive","Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### D-SFT-\>D-RL6k Accuracy: 31.33. Result ID: 69a89bbd6dbb7075b9517f56. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"step","Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### D-SFT-\>D-RL3k-\>D-RL6k Accuracy: 30.83. Result ID: 69a89bbd6dbb7075b9517f53. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"step","Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### D-SFT-\>D-RL6k Accuracy: 30.67. Result ID: 69a89bbd6dbb7075b9517f57. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"adaptive","Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### ThinkPrune(6k) Accuracy: 28.67. Result ID: 69a89bbd6dbb7075b9517f58. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"step","Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### ThinkPrune(6k-\>3k) Accuracy: 28.67. Result ID: 69a89bbd6dbb7075b9517f59. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"step","Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### D-SFT-\>D-RL6k Accuracy: 26.33. Result ID: 69a89bbd6dbb7075b9517f55. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"draft","Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### D-SFT-\>D-RL3k Accuracy: 22.33. Result ID: 69a89bbd6dbb7075b9517f51. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"draft","Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### D-SFT-\>D-RL3k-\>D-RL6k Accuracy: 22.33. Result ID: 69a89bbd6dbb7075b9517f52. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"draft","Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### D-SFT Accuracy: 12.5. Result ID: 69a89bbd6dbb7075b9517f50. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt":"draft","Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.