# Mathematical Reasoning on MATH500 (Pass@8/Avg@8) Source: [Mathematical Reasoning on MATH500 (Pass@8/Avg@8)]() Collection index: [llms.txt]() Data updated: 2026-05-11T10:31:22.155Z Evaluation of model performance on the MATH500 dataset for mathematical reasoning, specifically reporting results derived from 8 sampling attempts (Pass@8 and Avg@8). 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) | MATH500 | | Metric | Avg Score (@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 - [Avg Score (@8)](): Higher is better; unit: PERCENT. - [Pass@8](): Higher is better; unit: PERCENT. - [Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Avg Score (@8) | Result date | Report paper | | --- | --- | --- | --- | | vOPDtop-k | 79.3 | Not recorded | 6a0162c0dbc836b87d8233b0 | | vOPDfull-V | 78.9 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPDfull-V | 78.6 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPD | 75.2 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPDtop-k | 75 | Not recorded | 6a0162c0dbc836b87d8233b0 | | vOPDtop-k | 64.9 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPDfull-V | 64.6 | Not recorded | 6a0162c0dbc836b87d8233b0 | | vOPDfull-V | 64.4 | Not recorded | 6a0162c0dbc836b87d8233b0 | | vOPDfull-V | 64 | Not recorded | 6a0162c0dbc836b87d8233b0 | | vOPDtop-k | 64 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPDfull-V | 62.8 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPD | 61.2 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPDtop-k | 58.8 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPD | 58.7 | Not recorded | 6a0162c0dbc836b87d8233b0 | | OPDtop-k | 58 | Not recorded | 6a0162c0dbc836b87d8233b0 | | Student | 51.1 | Not recorded | 6a0162c0dbc836b87d8233b0 | | Student | 43.1 | Not recorded | 6a0162c0dbc836b87d8233b0 | | Student | 42.3 | Not recorded | 6a0162c0dbc836b87d8233b0 | ### vOPDtop-k Avg Score (@8): 79.3. Result ID: 6a01aff747f34ce924e43f4a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-4B → Qwen3-4B-Base"}. This record does not assert independent reproduction. ### vOPDfull-V Avg Score (@8): 78.9. Result ID: 6a01aff747f34ce924e43f4b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-4B → Qwen3-4B-Base"}. This record does not assert independent reproduction. ### OPDfull-V Avg Score (@8): 78.6. Result ID: 6a01aff747f34ce924e43f49. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-4B → Qwen3-4B-Base"}. This record does not assert independent reproduction. ### OPD Avg Score (@8): 75.2. Result ID: 6a01aff747f34ce924e43f47. [Reporting paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-4B → Qwen3-4B-Base"}. This record does not assert independent reproduction. ### OPDtop-k Avg Score (@8): 75. Result ID: 6a01aff747f34ce924e43f48. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Setup":"Qwen3-4B → Qwen3-4B-Base"}. This record does not assert independent reproduction. ### vOPDtop-k Avg Score (@8): 64.9. Result ID: 6a01aff747f34ce924e43f44. [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 Avg Score (@8): 64.6. Result ID: 6a01aff747f34ce924e43f43. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-1.7B → Qwen3-1.7B-Base"}. This record does not assert independent reproduction. ### vOPDfull-V Avg Score (@8): 64.4. Result ID: 6a01aff747f34ce924e43f51. [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 Avg Score (@8): 64. Result ID: 6a01aff747f34ce924e43f45. [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 Avg Score (@8): 64. Result ID: 6a01aff747f34ce924e43f50. [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. ### OPDfull-V Avg Score (@8): 62.8. Result ID: 6a01aff747f34ce924e43f4f. [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. ### OPD Avg Score (@8): 61.2. Result ID: 6a01aff747f34ce924e43f4d. [Reporting paper]() Recorded evaluation configuration: {"Model Setup":"Olmo-3-7B-Think → Olmo-3-7B-Base"}. This record does not assert independent reproduction. ### OPDtop-k Avg Score (@8): 58.8. Result ID: 6a01aff747f34ce924e43f4e. [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. ### OPD Avg Score (@8): 58.7. Result ID: 6a01aff747f34ce924e43f41. [Reporting paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-1.7B → Qwen3-1.7B-Base"}. This record does not assert independent reproduction. ### OPDtop-k Avg Score (@8): 58. Result ID: 6a01aff747f34ce924e43f42. [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 Avg Score (@8): 51.1. Result ID: 6a01aff747f34ce924e43f46. [Reporting paper]() Recorded evaluation configuration: {"Model Setup":"Qwen3-4B → Qwen3-4B-Base"}. This record does not assert independent reproduction. ### Student Avg Score (@8): 43.1. Result ID: 6a01aff747f34ce924e43f4c. [Reporting paper]() Recorded evaluation configuration: {"Model Setup":"Olmo-3-7B-Think → Olmo-3-7B-Base"}. This record does not assert independent reproduction. ### Student Avg Score (@8): 42.3. Result ID: 6a01aff747f34ce924e43f40. [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.