# Mathematical Reasoning on AIME 24/25 (Pass@32, Avg) Source: [Mathematical Reasoning on AIME 24/25 (Pass@32, Avg)]() Collection index: [llms.txt]() Data updated: 2026-05-11T10:31:22.226Z Evaluation of model performance on the combined AIME 2024 and 2025 datasets for mathematical reasoning, reporting scores based on sampling methods (Pass@32, Avg@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 24/25 | | Metric | Average Score (Pass@32) | | 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 - [Average Score (Pass@32)](): Higher is better; unit: PERCENT. - [Pass@32](): Higher is better; unit: PERCENT. - [Overall Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Score (Pass@32) | Result date | Report paper | | --- | --- | --- | --- | | OPDfull-V | 14.3 | Not recorded | 6a0162c0dbc836b87d8233b0 | | vOPDfull-V | 13.5 | Not recorded | 6a0162c0dbc836b87d8233b0 | | vOPDtop-k | 13.2 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPD | 10.4 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPDtop-k | 10.1 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPDfull-V | 8.6 | Not recorded | 6a0162c0dbc836b87d8233b0 | | vOPDtop-k | 8.4 | Not recorded | 6a0162c0dbc836b87d8233b0 | | vOPDfull-V | 7.9 | Not recorded | 6a0162c0dbc836b87d8233b0 | | Student | 7.8 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPD | 7.4 | Not recorded | 6a0162c0dbc836b87d8233b0 | | vOPDfull-V | 6.2 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPDfull-V | 5.8 | Not recorded | 6a0162c0dbc836b87d8233b0 | | vOPDtop-k | 5.6 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPDtop-k | 5.5 | Not recorded | 6a0162c0dbc836b87d8233b0 | | Student | 5.4 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPD | 4.8 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPDtop-k | 4 | Not recorded | 6a0162c0dbc836b87d8233b0 | | Student | 3 | Not recorded | 6a0162c0dbc836b87d8233b0 | ### OPDfull-V Average Score (Pass@32): 14.3. Result ID: 6a01aff747f34ce924e43f6d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-4B → Qwen3-4B-Base"}. This record does not assert independent reproduction. ### vOPDfull-V Average Score (Pass@32): 13.5. Result ID: 6a01aff747f34ce924e43f6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-4B → Qwen3-4B-Base"}. This record does not assert independent reproduction. ### vOPDtop-k Average Score (Pass@32): 13.2. Result ID: 6a01aff747f34ce924e43f6e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-4B → Qwen3-4B-Base"}. This record does not assert independent reproduction. ### OPD Average Score (Pass@32): 10.4. Result ID: 6a01aff747f34ce924e43f6b. [Reporting paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-4B → Qwen3-4B-Base"}. This record does not assert independent reproduction. ### OPDtop-k Average Score (Pass@32): 10.1. Result ID: 6a01aff747f34ce924e43f6c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Setup":"Qwen3-4B → Qwen3-4B-Base"}. This record does not assert independent reproduction. ### OPDfull-V Average Score (Pass@32): 8.6. Result ID: 6a01aff747f34ce924e43f73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Setup":"Olmo-3-7B-Think → Olmo-3-7B-Base"}. This record does not assert independent reproduction. ### vOPDtop-k Average Score (Pass@32): 8.4. Result ID: 6a01aff747f34ce924e43f74. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Setup":"Olmo-3-7B-Think → Olmo-3-7B-Base"}. This record does not assert independent reproduction. ### vOPDfull-V Average Score (Pass@32): 7.9. Result ID: 6a01aff747f34ce924e43f75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Setup":"Olmo-3-7B-Think → Olmo-3-7B-Base"}. This record does not assert independent reproduction. ### Student Average Score (Pass@32): 7.8. Result ID: 6a01aff747f34ce924e43f6a. [Reporting paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-4B → Qwen3-4B-Base"}. This record does not assert independent reproduction. ### OPD Average Score (Pass@32): 7.4. Result ID: 6a01aff747f34ce924e43f71. [Reporting paper]() Recorded evaluation configuration: {"Model Setup":"Olmo-3-7B-Think → Olmo-3-7B-Base"}. This record does not assert independent reproduction. ### vOPDfull-V Average Score (Pass@32): 6.2. Result ID: 6a01aff747f34ce924e43f69. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-1.7B → Qwen3-1.7B-Base"}. This record does not assert independent reproduction. ### OPDfull-V Average Score (Pass@32): 5.8. Result ID: 6a01aff747f34ce924e43f67. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-1.7B → Qwen3-1.7B-Base"}. This record does not assert independent reproduction. ### vOPDtop-k Average Score (Pass@32): 5.6. Result ID: 6a01aff747f34ce924e43f68. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-1.7B → Qwen3-1.7B-Base"}. This record does not assert independent reproduction. ### OPDtop-k Average Score (Pass@32): 5.5. Result ID: 6a01aff747f34ce924e43f72. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Setup":"Olmo-3-7B-Think → Olmo-3-7B-Base"}. This record does not assert independent reproduction. ### Student Average Score (Pass@32): 5.4. Result ID: 6a01aff747f34ce924e43f70. [Reporting paper]() Recorded evaluation configuration: {"Model Setup":"Olmo-3-7B-Think → Olmo-3-7B-Base"}. This record does not assert independent reproduction. ### OPD Average Score (Pass@32): 4.8. Result ID: 6a01aff747f34ce924e43f65. [Reporting paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-1.7B → Qwen3-1.7B-Base"}. This record does not assert independent reproduction. ### OPDtop-k Average Score (Pass@32): 4. Result ID: 6a01aff747f34ce924e43f66. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Setup":"Qwen3-1.7B → Qwen3-1.7B-Base"}. This record does not assert independent reproduction. ### Student Average Score (Pass@32): 3. Result ID: 6a01aff747f34ce924e43f64. [Reporting paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-1.7B → Qwen3-1.7B-Base"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.