# Mathematical Reasoning on GSM8k (Zero-shot Accuracy) Source: [Mathematical Reasoning on GSM8k (Zero-shot Accuracy)]() Collection index: [llms.txt]() Data updated: 2026-04-20T06:53:52.023Z Evaluation of model performance on the GSM8k mathematical reasoning dataset using zero-shot accuracy. 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) | GSM8k | | Metric | GSM8k Zero-shot Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 3 of 3 | | 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 - [GSM8k Zero-shot Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | GSM8k Zero-shot Accuracy | Result date | Report paper | | --- | --- | --- | --- | | StoSignSGD | 62.55 | Not recorded | 69e5b3057d0172140ec7df4b | | AdamW | 60.05 | Not recorded | 69e5b3057d0172140ec7df4b | | SignSGD | 48.07 | Not recorded | 69e5b3057d0172140ec7df4b | ### StoSignSGD GSM8k Zero-shot Accuracy: 62.55. Result ID: 69e5ccf547f34ce924cb69a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B","Fine-tuning Method":"LoRA","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### AdamW GSM8k Zero-shot Accuracy: 60.05. Result ID: 69e5ccf547f34ce924cb69a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B","Fine-tuning Method":"LoRA","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### SignSGD GSM8k Zero-shot Accuracy: 48.07. Result ID: 69e5ccf547f34ce924cb69a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen2.5-7B","Fine-tuning Method":"LoRA","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.