# Mathematical Reasoning on AIME 2025 (Avg@32, Pass@32) Source: [Mathematical Reasoning on AIME 2025 (Avg@32, Pass@32)]() Collection index: [llms.txt]() Data updated: 2026-04-14T11:14:59.615Z Evaluation of model performance on the American Invitational Mathematics Examination (AIME) 2025 dataset, reporting results using sampling parameters Avg@32 and Pass@32. 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) | AIME 2025 | | Metric | Average Score (Avg@32) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [Average Score (Avg@32)](): Higher is better; unit: SCALAR. - [Pass Rate (Pass@32)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Score (Avg@32) | Result date | Report paper | | --- | --- | --- | --- | | EAPO | 17.2 | Not recorded | 69ddca697d0172140ec79e8a | | DAPO | 17.1 | Not recorded | 69ddca697d0172140ec79e8a | | EntroAdv | 16.3 | Not recorded | 69ddca697d0172140ec79e8a | | Forking | 15.1 | Not recorded | 69ddca697d0172140ec79e8a | | KL-Cov | 13.8 | Not recorded | 69ddca697d0172140ec79e8a | | EntroReg | 12.6 | Not recorded | 69ddca697d0172140ec79e8a | | W-REINF | 10.1 | Not recorded | 69ddca697d0172140ec79e8a | | GRPO | 9.3 | Not recorded | 69ddca697d0172140ec79e8a | | PRIME | 6.1 | Not recorded | 69ddca697d0172140ec79e8a | | Base-7B | 5.1 | Not recorded | 69ddca697d0172140ec79e8a | ### EAPO Average Score (Avg@32): 17.2. Result ID: 69de21a847f34ce924c688b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Policy Entropy Method"}. This record does not assert independent reproduction. ### DAPO Average Score (Avg@32): 17.1. Result ID: 69de21a847f34ce924c688ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Classic RLVR Method"}. This record does not assert independent reproduction. ### EntroAdv Average Score (Avg@32): 16.3. Result ID: 69de21a847f34ce924c688ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Policy Entropy Method"}. This record does not assert independent reproduction. ### Forking Average Score (Avg@32): 15.1. Result ID: 69de21a847f34ce924c688ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Policy Entropy Method"}. This record does not assert independent reproduction. ### KL-Cov Average Score (Avg@32): 13.8. Result ID: 69de21a847f34ce924c688af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Policy Entropy Method"}. This record does not assert independent reproduction. ### EntroReg Average Score (Avg@32): 12.6. Result ID: 69de21a847f34ce924c688ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Policy Entropy Method"}. This record does not assert independent reproduction. ### W-REINF Average Score (Avg@32): 10.1. Result ID: 69de21a847f34ce924c688a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Classic RLVR Method"}. This record does not assert independent reproduction. ### GRPO Average Score (Avg@32): 9.3. Result ID: 69de21a847f34ce924c688aa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Classic RLVR Method"}. This record does not assert independent reproduction. ### PRIME Average Score (Avg@32): 6.1. Result ID: 69de21a847f34ce924c688a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Classic RLVR Method"}. This record does not assert independent reproduction. ### Base-7B Average Score (Avg@32): 5.1. Result ID: 69de21a847f34ce924c688a7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Classic RLVR Method"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.