# Mathematical Reasoning on AIME24, AIME25, MATH500, AMC23, Hmmt25, and Olympiad Source: [Mathematical Reasoning on AIME24, AIME25, MATH500, AMC23, Hmmt25, and Olympiad]() Collection index: [llms.txt]() Data updated: 2026-05-19T13:16:01.491Z Evaluation of Mathematical Reasoning performance across a specific suite comprising AIME 2024, AIME 2025, MATH500, AMC 2023, Hmmt 2025, and Olympiad components. 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) | Mathematical Reasoning Evaluation Suite (AIME24, AIME25, MATH500, AMC23, Hmmt25, Olympiad) | | Metric | AIME 2024 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 33 of 33 | | 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 - [AIME 2024 Score](): Higher is better; unit: PERCENT. - [AIME 2025 Score](): Higher is better; unit: PERCENT. - [MATH500 Score](): Higher is better; unit: PERCENT. - [AMC 2023 Score](): Higher is better; unit: PERCENT. - [Hmmt 2025 Score](): Higher is better; unit: PERCENT. - [Olympiad Score](): Higher is better; unit: PERCENT. - [Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | AIME 2024 Score | Result date | Report paper | | --- | --- | --- | --- | | IH-GRPO | 61.67 | Not recorded | 6a0bef15dbc836b87d82cae3 | | SimpleTIR | 58.33 | Not recorded | 6a0bef15dbc836b87d82cae3 | | Dr.GRPO | 57.5 | Not recorded | 6a0bef15dbc836b87d82cae3 | | Dr.GRPO | 56.35 | Not recorded | 6a0bef15dbc836b87d82cae3 | | DAPO | 56.15 | Not recorded | 6a0bef15dbc836b87d82cae3 | | EH-GRPO | 55.42 | Not recorded | 6a0bef15dbc836b87d82cae3 | | IH-GRPO | 55.31 | Not recorded | 6a0bef15dbc836b87d82cae3 | | SimpleTIR | 52.92 | Not recorded | 6a0bef15dbc836b87d82cae3 | | SimpleTIR | 51.98 | Not recorded | 6a0bef15dbc836b87d82cae3 | | Dr.GRPO | 51.67 | Not recorded | 6a0bef15dbc836b87d82cae3 | | DAPO | 51.56 | Not recorded | 6a0bef15dbc836b87d82cae3 | | DAPO | 50.1 | Not recorded | 6a0bef15dbc836b87d82cae3 | | Dr.GRPO | 49.69 | Not recorded | 6a0bef15dbc836b87d82cae3 | | DAPO | 49.38 | Not recorded | 6a0bef15dbc836b87d82cae3 | | SimpleTIR | 49.27 | Not recorded | 6a0bef15dbc836b87d82cae3 | | EH-GRPO | 41.77 | Not recorded | 6a0bef15dbc836b87d82cae3 | | STaR | 40.83 | Not recorded | 6a0bef15dbc836b87d82cae3 | | STaR | 38.85 | Not recorded | 6a0bef15dbc836b87d82cae3 | | Base | 34.69 | Not recorded | 6a0bef15dbc836b87d82cae3 | | Base | 34.17 | Not recorded | 6a0bef15dbc836b87d82cae3 | | STaR | 32.4 | Not recorded | 6a0bef15dbc836b87d82cae3 | | IH-GRPO | 31.15 | Not recorded | 6a0bef15dbc836b87d82cae3 | | Dr.GRPO | 29.37 | Not recorded | 6a0bef15dbc836b87d82cae3 | | SimpleTIR | 29.27 | Not recorded | 6a0bef15dbc836b87d82cae3 | | Dr.GRPO | 27.92 | Not recorded | 6a0bef15dbc836b87d82cae3 | | EH-GRPO | 27.81 | Not recorded | 6a0bef15dbc836b87d82cae3 | | SimpleTIR | 26.67 | Not recorded | 6a0bef15dbc836b87d82cae3 | | STaR | 26.35 | Not recorded | 6a0bef15dbc836b87d82cae3 | | DAPO | 25.73 | Not recorded | 6a0bef15dbc836b87d82cae3 | | DAPO | 24.9 | Not recorded | 6a0bef15dbc836b87d82cae3 | | Base | 22.5 | Not recorded | 6a0bef15dbc836b87d82cae3 | | STaR | 11.67 | Not recorded | 6a0bef15dbc836b87d82cae3 | | STaR | 11.25 | Not recorded | 6a0bef15dbc836b87d82cae3 | ### IH-GRPO AIME 2024 Score: 61.67. Result ID: 6a0c627efbc373592c04191f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Tool":"D"}. This record does not assert independent reproduction. ### SimpleTIR AIME 2024 Score: 58.33. Result ID: 6a0c627efbc373592c041919. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Tool":"D"}. This record does not assert independent reproduction. ### Dr.GRPO AIME 2024 Score: 57.5. Result ID: 6a0c627efbc373592c04191b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Tool":"D"}. This record does not assert independent reproduction. ### Dr.GRPO AIME 2024 Score: 56.35. Result ID: 6a0c627efbc373592c04191a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Tool":"C"}. This record does not assert independent reproduction. ### DAPO AIME 2024 Score: 56.15. Result ID: 6a0c627efbc373592c04191d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Tool":"D"}. This record does not assert independent reproduction. ### EH-GRPO AIME 2024 Score: 55.42. Result ID: 6a0c627efbc373592c04191e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Tool":"D"}. This record does not assert independent reproduction. ### IH-GRPO AIME 2024 Score: 55.31. Result ID: 6a0c627efbc373592c041914. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Tool":"D"}. This record does not assert independent reproduction. ### SimpleTIR AIME 2024 Score: 52.92. Result ID: 6a0c627efbc373592c041918. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Tool":"C"}. This record does not assert independent reproduction. ### SimpleTIR AIME 2024 Score: 51.98. Result ID: 6a0c627efbc373592c04190e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Tool":"D"}. This record does not assert independent reproduction. ### Dr.GRPO AIME 2024 Score: 51.67. Result ID: 6a0c627efbc373592c041910. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Tool":"D"}. This record does not assert independent reproduction. ### DAPO AIME 2024 Score: 51.56. Result ID: 6a0c627efbc373592c04191c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Tool":"C"}. This record does not assert independent reproduction. ### DAPO AIME 2024 Score: 50.1. Result ID: 6a0c627efbc373592c041912. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Tool":"D"}. This record does not assert independent reproduction. ### Dr.GRPO AIME 2024 Score: 49.69. Result ID: 6a0c627efbc373592c04190f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Tool":"C"}. This record does not assert independent reproduction. ### DAPO AIME 2024 Score: 49.38. Result ID: 6a0c627efbc373592c041911. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Tool":"C"}. This record does not assert independent reproduction. ### SimpleTIR AIME 2024 Score: 49.27. Result ID: 6a0c627efbc373592c04190d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Tool":"C"}. This record does not assert independent reproduction. ### EH-GRPO AIME 2024 Score: 41.77. Result ID: 6a0c627efbc373592c041913. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Tool":"D"}. This record does not assert independent reproduction. ### STaR AIME 2024 Score: 40.83. Result ID: 6a0c627efbc373592c041917. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Tool":"D"}. This record does not assert independent reproduction. ### STaR AIME 2024 Score: 38.85. Result ID: 6a0c627efbc373592c041916. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Tool":"C"}. This record does not assert independent reproduction. ### Base AIME 2024 Score: 34.69. Result ID: 6a0c627efbc373592c041915. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Tool":"No"}. This record does not assert independent reproduction. ### Base AIME 2024 Score: 34.17. Result ID: 6a0c627efbc373592c04190a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Tool":"No"}. This record does not assert independent reproduction. ### STaR AIME 2024 Score: 32.4. Result ID: 6a0c627efbc373592c04190c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Tool":"D"}. This record does not assert independent reproduction. ### IH-GRPO AIME 2024 Score: 31.15. Result ID: 6a0c627efbc373592c041909. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Tool":"D"}. This record does not assert independent reproduction. ### Dr.GRPO AIME 2024 Score: 29.37. Result ID: 6a0c627efbc373592c041905. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Tool":"D"}. This record does not assert independent reproduction. ### SimpleTIR AIME 2024 Score: 29.27. Result ID: 6a0c627efbc373592c041903. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Tool":"D"}. This record does not assert independent reproduction. ### Dr.GRPO AIME 2024 Score: 27.92. Result ID: 6a0c627efbc373592c041904. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Tool":"C"}. This record does not assert independent reproduction. ### EH-GRPO AIME 2024 Score: 27.81. Result ID: 6a0c627efbc373592c041908. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Tool":"D"}. This record does not assert independent reproduction. ### SimpleTIR AIME 2024 Score: 26.67. Result ID: 6a0c627efbc373592c041902. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Tool":"C"}. This record does not assert independent reproduction. ### STaR AIME 2024 Score: 26.35. Result ID: 6a0c627efbc373592c04190b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B","Tool":"C"}. This record does not assert independent reproduction. ### DAPO AIME 2024 Score: 25.73. Result ID: 6a0c627efbc373592c041906. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Tool":"C"}. This record does not assert independent reproduction. ### DAPO AIME 2024 Score: 24.9. Result ID: 6a0c627efbc373592c041907. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Tool":"D"}. This record does not assert independent reproduction. ### Base AIME 2024 Score: 22.5. Result ID: 6a0c627efbc373592c0418ff. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Tool":"No"}. This record does not assert independent reproduction. ### STaR AIME 2024 Score: 11.67. Result ID: 6a0c627efbc373592c041901. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Tool":"D"}. This record does not assert independent reproduction. ### STaR AIME 2024 Score: 11.25. Result ID: 6a0c627efbc373592c041900. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-1.7B","Tool":"C"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.