# Mathematical Reasoning on MATH-500 n=200 (pilot) Source: [Mathematical Reasoning on MATH-500 n=200 (pilot)]() Collection index: [llms.txt]() Data updated: 2026-05-11T10:03:04.647Z Evaluation of model performance on the specific n=200 pilot subset of the MATH-500 dataset for mathematical reasoning, reporting standard accuracy (Acc) and average token usage (Avg Tok). 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) | MATH-500 n=200 (pilot) | | Metric | Accuracy (%) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 4 of 4 | | 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 (%)](): Higher is better; unit: PERCENT. - [Average Tokens](): Lower is better; unit: SCALAR. ## Recorded results | Method | Accuracy (%) | Result date | Report paper | | --- | --- | --- | --- | | Town@1024 | 69.5 | Not recorded | 6a0162b8dbc836b87d8232fd | | Mrsd (3-round) | 61 | Not recorded | 6a0162b8dbc836b87d8232fd | | Nothink@B1 | 47.5 | Not recorded | 6a0162b8dbc836b87d8232fd | | Think@Bthink | 19.5 | Not recorded | 6a0162b8dbc836b87d8232fd | ### Town@1024 Accuracy (%): 69.5. Result ID: 6a01a95847f34ce924e40f6f. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B","Decoding Strategy":"greedy decoding"}. This record does not assert independent reproduction. ### Mrsd (3-round) Accuracy (%): 61. Result ID: 6a01a95847f34ce924e40f70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B","Decoding Strategy":"greedy decoding"}. This record does not assert independent reproduction. ### Nothink@B1 Accuracy (%): 47.5. Result ID: 6a01a95847f34ce924e40f6d. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B","Decoding Strategy":"greedy decoding"}. This record does not assert independent reproduction. ### Think@Bthink Accuracy (%): 19.5. Result ID: 6a01a95847f34ce924e40f6e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B","Decoding Strategy":"greedy decoding"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.