# Mathematical Reasoning on AIME 2025 (AIME25, Math Avg) Source: [Mathematical Reasoning on AIME 2025 (AIME25, Math Avg)]() Collection index: [llms.txt]() Data updated: 2026-04-14T08:24:26.570Z Evaluation of model performance on the American Invitational Mathematics Examination (AIME) 2025 dataset, reporting AIME25 score and Math Average. 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 | AIME25 Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [AIME25 Score](): Higher is better; unit: SCALAR. - [Math Average](): Higher is better; unit: SCALAR. ## Recorded results | Method | AIME25 Score | Result date | Report paper | | --- | --- | --- | --- | | PSFT | 48.38 | Not recorded | 68fa7ae21e209131cea85a73 | | SFT | 46.88 | Not recorded | 68fa7ae21e209131cea85a73 | | Granite-3.3 (8B) | 27.96 | Not recorded | 69bb82ec0636e5bf4afc18a2 | | Mistral-Small (24B) | 27.34 | Not recorded | 69bb82ec0636e5bf4afc18a2 | | Mistral-7B | 24.27 | Not recorded | 69bb82ec0636e5bf4afc18a2 | | Granite-4-H Micro (3B) | 23.49 | Not recorded | 69bb82ec0636e5bf4afc18a2 | | Nemotron-H-8k (8B) | 22.76 | Not recorded | 69bb82ec0636e5bf4afc18a2 | | Granite-4 Micro (3B) | 22.29 | Not recorded | 69bb82ec0636e5bf4afc18a2 | | LLaMA-3.1 (8B) | 19.32 | Not recorded | 69bb82ec0636e5bf4afc18a2 | | Granite-4 Micro (3B) | 12.34 | Not recorded | 69bb82ec0636e5bf4afc18a2 | | Granite-4-H Micro (3B) | 2.7 | Not recorded | 69bb82ec0636e5bf4afc18a2 | | Nemotron-H-8k (8B) | 2.29 | Not recorded | 69bb82ec0636e5bf4afc18a2 | | Mistral-Small (24B) | 0.73 | Not recorded | 69bb82ec0636e5bf4afc18a2 | | Granite-3.3 (8B) | 0.31 | Not recorded | 69bb82ec0636e5bf4afc18a2 | | LLaMA-3.1 (8B) | 0.15 | Not recorded | 69bb82ec0636e5bf4afc18a2 | | Mistral-7B | 0.1 | Not recorded | 69bb82ec0636e5bf4afc18a2 | ### PSFT AIME25 Score: 48.38. Result ID: 69ddf9b647f34ce924c55c0b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SFT AIME25 Score: 46.88. Result ID: 69ddf9b647f34ce924c55c0c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Granite-3.3 (8B) AIME25 Score: 27.96. Result ID: 69bb9fae47f34ce924a51dcb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"PRISM"}. This record does not assert independent reproduction. ### Mistral-Small (24B) AIME25 Score: 27.34. Result ID: 69bb9fae47f34ce924a51dd7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"PRISM"}. This record does not assert independent reproduction. ### Mistral-7B AIME25 Score: 24.27. Result ID: 69bb9fae47f34ce924a51dd3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"PRISM"}. This record does not assert independent reproduction. ### Granite-4-H Micro (3B) AIME25 Score: 23.49. Result ID: 69bb9fae47f34ce924a51dcf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"PRISM"}. This record does not assert independent reproduction. ### Nemotron-H-8k (8B) AIME25 Score: 22.76. Result ID: 69bb9fae47f34ce924a51dd1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"PRISM"}. This record does not assert independent reproduction. ### Granite-4 Micro (3B) AIME25 Score: 22.29. Result ID: 69bb9fae47f34ce924a51dcd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"PRISM"}. This record does not assert independent reproduction. ### LLaMA-3.1 (8B) AIME25 Score: 19.32. Result ID: 69bb9fae47f34ce924a51dd5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"PRISM"}. This record does not assert independent reproduction. ### Granite-4 Micro (3B) AIME25 Score: 12.34. Result ID: 69bb9fae47f34ce924a51dcc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Base"}. This record does not assert independent reproduction. ### Granite-4-H Micro (3B) AIME25 Score: 2.7. Result ID: 69bb9fae47f34ce924a51dce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Base"}. This record does not assert independent reproduction. ### Nemotron-H-8k (8B) AIME25 Score: 2.29. Result ID: 69bb9fae47f34ce924a51dd0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Base"}. This record does not assert independent reproduction. ### Mistral-Small (24B) AIME25 Score: 0.73. Result ID: 69bb9fae47f34ce924a51dd6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Base"}. This record does not assert independent reproduction. ### Granite-3.3 (8B) AIME25 Score: 0.31. Result ID: 69bb9fae47f34ce924a51dca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Base"}. This record does not assert independent reproduction. ### LLaMA-3.1 (8B) AIME25 Score: 0.15. Result ID: 69bb9fae47f34ce924a51dd4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Base"}. This record does not assert independent reproduction. ### Mistral-7B AIME25 Score: 0.1. Result ID: 69bb9fae47f34ce924a51dd2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Variant":"Base"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.