# Mathematical Reasoning on AIME25 (ACC/maj@8) Source: [Mathematical Reasoning on AIME25 (ACC/maj@8)]() Collection index: [llms.txt]() Data updated: 2026-04-16T08:23:47.136Z Evaluation of model performance on the AIME 2025 dataset for mathematical reasoning, specifically measured using the ACC/maj@8 metric. 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) | AIME25 | | Metric | ACC/maj@8 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [ACC/maj@8](): Higher is better; unit: PERCENT. ## Recorded results | Method | ACC/maj@8 | Result date | Report paper | | --- | --- | --- | --- | | GRPO | 33.33 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | DAPO | 33.33 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | DAPO w/ EL | 33.33 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | CDE | 33.33 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | DiPO | 33.33 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | DAPO | 30 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | DAPO w/ EL | 30 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | CDE | 30 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | DiPO | 30 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | GRPO | 26.67 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | GRPO | 26.67 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | DAPO | 23.33 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | DiPO | 23.33 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | DAPO w/ EL | 20 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | CDE | 20 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | Base model | 13.33 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | Base model | 6.67 | Not recorded | 69e06d2c7d0172140ec7cbb5 | | Base model | 3.33 | Not recorded | 69e06d2c7d0172140ec7cbb5 | ### GRPO ACC/maj@8: 33.33. Result ID: 69e09c9047f34ce924c9d162. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B-Base"}. This record does not assert independent reproduction. ### DAPO ACC/maj@8: 33.33. Result ID: 69e09c9047f34ce924c9d163. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B-Base"}. This record does not assert independent reproduction. ### DAPO w/ EL ACC/maj@8: 33.33. Result ID: 69e09c9047f34ce924c9d164. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B-Base"}. This record does not assert independent reproduction. ### CDE ACC/maj@8: 33.33. Result ID: 69e09c9047f34ce924c9d165. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B-Base"}. This record does not assert independent reproduction. ### DiPO ACC/maj@8: 33.33. Result ID: 69e09c9047f34ce924c9d166. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B-Base"}. This record does not assert independent reproduction. ### DAPO ACC/maj@8: 30. Result ID: 69e09c9047f34ce924c9d15d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Base"}. This record does not assert independent reproduction. ### DAPO w/ EL ACC/maj@8: 30. Result ID: 69e09c9047f34ce924c9d15e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Base"}. This record does not assert independent reproduction. ### CDE ACC/maj@8: 30. Result ID: 69e09c9047f34ce924c9d15f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Base"}. This record does not assert independent reproduction. ### DiPO ACC/maj@8: 30. Result ID: 69e09c9047f34ce924c9d160. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Base"}. This record does not assert independent reproduction. ### GRPO ACC/maj@8: 26.67. Result ID: 69e09c9047f34ce924c9d15c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Base"}. This record does not assert independent reproduction. ### GRPO ACC/maj@8: 26.67. Result ID: 69e09c9047f34ce924c9d168. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### DAPO ACC/maj@8: 23.33. Result ID: 69e09c9047f34ce924c9d169. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### DiPO ACC/maj@8: 23.33. Result ID: 69e09c9047f34ce924c9d16c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### DAPO w/ EL ACC/maj@8: 20. Result ID: 69e09c9047f34ce924c9d16a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### CDE ACC/maj@8: 20. Result ID: 69e09c9047f34ce924c9d16b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### Base model ACC/maj@8: 13.33. Result ID: 69e09c9047f34ce924c9d161. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B-Base"}. This record does not assert independent reproduction. ### Base model ACC/maj@8: 6.67. Result ID: 69e09c9047f34ce924c9d15b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B-Base"}. This record does not assert independent reproduction. ### Base model ACC/maj@8: 3.33. Result ID: 69e09c9047f34ce924c9d167. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.