# Mathematical Reasoning on AIME 25 (Accuracy (pass@1)) Source: [Mathematical Reasoning on AIME 25 (Accuracy (pass@1))]() Collection index: [llms.txt]() Data updated: 2026-05-14T06:44:57.333Z Evaluation of model performance on the AIME 25 dataset for mathematical reasoning, specifically reporting the success rate using the Accuracy (pass@1) 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) | AIME 25 | | Metric | Accuracy (pass@1) | | 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 - [Accuracy (pass@1)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (pass@1) | Result date | Report paper | | --- | --- | --- | --- | | Critique | 37.29 | Not recorded | 68fa79691e209131cea7d795 | | Wait | 36.77 | Not recorded | 68fa79691e209131cea7d795 | | Alternatively | 36.51 | Not recorded | 68fa79691e209131cea7d795 | | Hmm | 36.51 | Not recorded | 68fa79691e209131cea7d795 | | Baseline (w/o BF) | 36.41 | Not recorded | 68fa79691e209131cea7d795 | | Learned | 36.09 | Not recorded | 68fa79691e209131cea7d795 | | Wait | 30.26 | Not recorded | 68fa79691e209131cea7d795 | | Learned | 30.26 | Not recorded | 68fa79691e209131cea7d795 | | Hmm | 30.1 | Not recorded | 68fa79691e209131cea7d795 | | Critique | 29.9 | Not recorded | 68fa79691e209131cea7d795 | | Alternatively | 29.64 | Not recorded | 68fa79691e209131cea7d795 | | Baseline (w/o BF) | 29.32 | Not recorded | 68fa79691e209131cea7d795 | | Hmm | 23.85 | Not recorded | 68fa79691e209131cea7d795 | | Alternatively | 23.8 | Not recorded | 68fa79691e209131cea7d795 | | Wait | 23.49 | Not recorded | 68fa79691e209131cea7d795 | | Baseline (w/o BF) | 23.33 | Not recorded | 68fa79691e209131cea7d795 | | Critique | 22.45 | Not recorded | 68fa79691e209131cea7d795 | | Learned | 22.4 | Not recorded | 68fa79691e209131cea7d795 | ### Critique Accuracy (pass@1): 37.29. Result ID: 6a056df147f34ce924ebc021. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Qwen-7B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Wait Accuracy (pass@1): 36.77. Result ID: 6a056df147f34ce924ebc020. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Qwen-7B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Alternatively Accuracy (pass@1): 36.51. Result ID: 6a056df147f34ce924ebc01e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Qwen-7B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Hmm Accuracy (pass@1): 36.51. Result ID: 6a056df147f34ce924ebc01f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Qwen-7B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Baseline (w/o BF) Accuracy (pass@1): 36.41. Result ID: 6a056df147f34ce924ebc01d. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Qwen-7B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Learned Accuracy (pass@1): 36.09. Result ID: 6a056df147f34ce924ebc022. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Qwen-7B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Wait Accuracy (pass@1): 30.26. Result ID: 6a056df147f34ce924ebc026. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Llama-8B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Learned Accuracy (pass@1): 30.26. Result ID: 6a056df147f34ce924ebc028. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Llama-8B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Hmm Accuracy (pass@1): 30.1. Result ID: 6a056df147f34ce924ebc025. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Llama-8B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Critique Accuracy (pass@1): 29.9. Result ID: 6a056df147f34ce924ebc027. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Llama-8B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Alternatively Accuracy (pass@1): 29.64. Result ID: 6a056df147f34ce924ebc024. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Llama-8B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Baseline (w/o BF) Accuracy (pass@1): 29.32. Result ID: 6a056df147f34ce924ebc023. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Llama-8B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Hmm Accuracy (pass@1): 23.85. Result ID: 6a056df147f34ce924ebc019. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Qwen-1.5B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Alternatively Accuracy (pass@1): 23.8. Result ID: 6a056df147f34ce924ebc018. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Qwen-1.5B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Wait Accuracy (pass@1): 23.49. Result ID: 6a056df147f34ce924ebc01a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Qwen-1.5B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Baseline (w/o BF) Accuracy (pass@1): 23.33. Result ID: 6a056df147f34ce924ebc017. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Qwen-1.5B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Critique Accuracy (pass@1): 22.45. Result ID: 6a056df147f34ce924ebc01b. [Reporting paper]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Qwen-1.5B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. ### Learned Accuracy (pass@1): 22.4. Result ID: 6a056df147f34ce924ebc01c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone Model":"DS-R1-Qwen-1.5B","Cmax":"3","Bmax":"9216"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.