# Mathematical Reasoning on Aggregate (AIME, AMC, MATH, Minerva, Olympiad) Source: [Mathematical Reasoning on Aggregate (AIME, AMC, MATH, Minerva, Olympiad)]() Collection index: [llms.txt]() Data updated: 2026-04-14T11:14:59.676Z Evaluation of Mathematical Reasoning performance across an aggregate benchmark comprising AIME, AMC, MATH, Minerva, and Olympiad datasets, reporting the average score. 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) | Aggregate (AIME, AMC, MATH, Minerva, Olympiad) | | Metric | Average Score | | Unit | PERCENT | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Score | Result date | Report paper | | --- | --- | --- | --- | | EAPO | 48.6 | Not recorded | 69ddca697d0172140ec79e8a | | Forking | 47.9 | Not recorded | 69ddca697d0172140ec79e8a | | EntroAdv | 47.9 | Not recorded | 69ddca697d0172140ec79e8a | | DAPO | 47.2 | Not recorded | 69ddca697d0172140ec79e8a | | KL-Cov | 46.4 | Not recorded | 69ddca697d0172140ec79e8a | | EntroReg | 46.2 | Not recorded | 69ddca697d0172140ec79e8a | | GRPO | 43.8 | Not recorded | 69ddca697d0172140ec79e8a | | W-REINF | 41.6 | Not recorded | 69ddca697d0172140ec79e8a | | PRIME | 30.1 | Not recorded | 69ddca697d0172140ec79e8a | | Base-7B | 20.8 | Not recorded | 69ddca697d0172140ec79e8a | ### EAPO Average Score: 48.6. Result ID: 69de21a847f34ce924c688e2. [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: 47.9. Result ID: 69de21a847f34ce924c688df. [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. ### EntroAdv Average Score: 47.9. Result ID: 69de21a847f34ce924c688e0. [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: 47.2. Result ID: 69de21a847f34ce924c688dd. [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. ### KL-Cov Average Score: 46.4. Result ID: 69de21a847f34ce924c688e1. [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: 46.2. Result ID: 69de21a847f34ce924c688de. [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. ### GRPO Average Score: 43.8. Result ID: 69de21a847f34ce924c688dc. [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. ### W-REINF Average Score: 41.6. Result ID: 69de21a847f34ce924c688db. [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. ### PRIME Average Score: 30.1. Result ID: 69de21a847f34ce924c688da. [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: 20.8. Result ID: 69de21a847f34ce924c688d9. [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.