# Math and Text Reasoning on Olympiad Bench Source: [Math and Text Reasoning on Olympiad Bench]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:54:51.507Z Evaluation of model performance on math and text reasoning tasks using the Olympiad Bench dataset, measured by 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) | Olympiad Bench | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | PAQ | Result date | Report paper | | --- | --- | --- | --- | | UCPO | 73.67 | Not recorded | 69802f68a8b01e76cc8e14db | | Prompt-UC | 71.49 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 70.84 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 70.68 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 70.68 | Not recorded | 69802f68a8b01e76cc8e14db | | Baseline | 69.63 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO | 69.22 | Not recorded | 69802f68a8b01e76cc8e14db | | UCPO | 25.56 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 19.28 | Not recorded | 69802f68a8b01e76cc8e14db | | Prompt-UC | 17.45 | Not recorded | 69802f68a8b01e76cc8e14db | | Baseline | 14.96 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO | 14.76 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 13.58 | Not recorded | 69802f68a8b01e76cc8e14db | | GRPO-UC | 12.9 | Not recorded | 69802f68a8b01e76cc8e14db | ### UCPO PAQ: 73.67. Result ID: 699615925698665ec4552143. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Prompt-UC PAQ: 71.49. Result ID: 699615925698665ec455213e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### GRPO-UC PAQ: 70.84. Result ID: 699615925698665ec4552141. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Reward Coefficient (ru)":"0.5"}. This record does not assert independent reproduction. ### GRPO-UC PAQ: 70.68. Result ID: 699615925698665ec4552140. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Reward Coefficient (ru)":"0.2"}. This record does not assert independent reproduction. ### GRPO-UC PAQ: 70.68. Result ID: 699615925698665ec4552142. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Reward Coefficient (ru)":"0.8"}. This record does not assert independent reproduction. ### Baseline PAQ: 69.63. Result ID: 699615925698665ec455213d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### GRPO PAQ: 69.22. Result ID: 699615925698665ec455213f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### UCPO PAQ: 25.56. Result ID: 699615925698665ec455214a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### GRPO-UC PAQ: 19.28. Result ID: 699615925698665ec4552148. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Reward Coefficient (ru)":"0.5"}. This record does not assert independent reproduction. ### Prompt-UC PAQ: 17.45. Result ID: 699615925698665ec4552145. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Baseline PAQ: 14.96. Result ID: 699615925698665ec4552144. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### GRPO PAQ: 14.76. Result ID: 699615925698665ec4552146. [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: 13.58. Result ID: 699615925698665ec4552147. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Reward Coefficient (ru)":"0.2"}. This record does not assert independent reproduction. ### GRPO-UC PAQ: 12.9. Result ID: 699615925698665ec4552149. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Reward Coefficient (ru)":"0.8"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.