# Math and Text Reasoning on MATH 500 Source: [Math and Text Reasoning on MATH 500]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:54:51.476Z Evaluation of model performance on the MATH 500 dataset focusing on math and text reasoning, measured using PAQ and F1 scores. 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 | Math and Text Reasoning | | Dataset (including any stated split) | MATH 500 | | Metric | PAQ | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [PAQ](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | PAQ | Result date | Report paper | | --- | --- | --- | --- | | UCPO | 97.28 | Not recorded | 69802f68a8b01e76cc8e14db | | Baseline | 96.8 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO | 96.46 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 96.31 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 96.24 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 96.2 | Not recorded | 69802f68a8b01e76cc8e14db | | Prompt-UC | 95.8 | Not recorded | 69802f68a8b01e76cc8e14db | | UCPO | 60.95 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 57.61 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 56.61 | Not recorded | 69802f68a8b01e76cc8e14db | | Prompt-UC | 47.32 | Not recorded | 69802f68a8b01e76cc8e14db | | Baseline | 45.8 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO | 43.96 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 40.98 | Not recorded | 69802f68a8b01e76cc8e14db | ### UCPO PAQ: 97.28. Result ID: 699615925698665ec4552127. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Baseline PAQ: 96.8. Result ID: 699615925698665ec4552121. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### GRPO PAQ: 96.46. Result ID: 699615925698665ec4552123. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### GRPO-UC PAQ: 96.31. Result ID: 699615925698665ec4552124. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Reward Coefficient (ru)":"0.2"}. This record does not assert independent reproduction. ### GRPO-UC PAQ: 96.24. Result ID: 699615925698665ec4552125. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Reward Coefficient (ru)":"0.5"}. This record does not assert independent reproduction. ### GRPO-UC PAQ: 96.2. Result ID: 699615925698665ec4552126. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Reward Coefficient (ru)":"0.8"}. This record does not assert independent reproduction. ### Prompt-UC PAQ: 95.8. Result ID: 699615925698665ec4552122. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### UCPO PAQ: 60.95. Result ID: 699615925698665ec455212e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### GRPO-UC PAQ: 57.61. Result ID: 699615925698665ec455212c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Reward Coefficient (ru)":"0.5"}. This record does not assert independent reproduction. ### GRPO-UC PAQ: 56.61. Result ID: 699615925698665ec455212d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Reward Coefficient (ru)":"0.8"}. This record does not assert independent reproduction. ### Prompt-UC PAQ: 47.32. Result ID: 699615925698665ec4552129. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Baseline PAQ: 45.8. Result ID: 699615925698665ec4552128. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### GRPO PAQ: 43.96. Result ID: 699615925698665ec455212a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### GRPO-UC PAQ: 40.98. Result ID: 699615925698665ec455212b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Reward Coefficient (ru)":"0.2"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.