# Mathematical Reasoning on GradeMath (pass@1) Source: [Mathematical Reasoning on GradeMath (pass@1)]() Collection index: [llms.txt]() Data updated: 2026-03-11T07:55:21.820Z Evaluation of model performance on the GradeMath dataset for mathematical reasoning, specifically using the 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) | GradeMath | | Metric | Pass@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 - [Pass@1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pass@1 | Result date | Report paper | | --- | --- | --- | --- | | SGPO | 64.76 | Not recorded | 68fa7bbf1e209131cea8a2ae | | GRPO | 63.81 | Not recorded | 68fa7bbf1e209131cea8a2ae | | Baseline | 62.38 | Not recorded | 68fa7bbf1e209131cea8a2ae | | Baseline | 53.81 | Not recorded | 68fa7bbf1e209131cea8a2ae | | SGPO | 53.81 | Not recorded | 68fa7bbf1e209131cea8a2ae | | SGPO | 53.33 | Not recorded | 68fa7bbf1e209131cea8a2ae | | GRPO | 52.86 | Not recorded | 68fa7bbf1e209131cea8a2ae | | Baseline | 49.52 | Not recorded | 68fa7bbf1e209131cea8a2ae | | SGPO | 47.17 | Not recorded | 68fa7bbf1e209131cea8a2ae | | GRPO | 47.14 | Not recorded | 68fa7bbf1e209131cea8a2ae | | SGPO | 46.67 | Not recorded | 68fa7bbf1e209131cea8a2ae | | SGPO | 46.19 | Not recorded | 68fa7bbf1e209131cea8a2ae | | SGPO | 45.24 | Not recorded | 68fa7bbf1e209131cea8a2ae | | GRPO | 43.33 | Not recorded | 68fa7bbf1e209131cea8a2ae | | SGPO | 42.38 | Not recorded | 68fa7bbf1e209131cea8a2ae | | Baseline | 41.43 | Not recorded | 68fa7bbf1e209131cea8a2ae | | SGPO | 29.05 | Not recorded | 68fa7bbf1e209131cea8a2ae | | GRPO | 28.33 | Not recorded | 68fa7bbf1e209131cea8a2ae | | Baseline | 23.81 | Not recorded | 68fa7bbf1e209131cea8a2ae | ### SGPO Pass@1: 64.76. Result ID: 69b11fe66dbb7075b95b4da5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"QwQ-32B","Judge Model":"DeepSeek-V3-0324"}. This record does not assert independent reproduction. ### GRPO Pass@1: 63.81. Result ID: 69b11fe66dbb7075b95b4da4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Baseline Pass@1: 62.38. Result ID: 69b11fe66dbb7075b95b4da3. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Baseline Pass@1: 53.81. Result ID: 69b11fe66dbb7075b95b4da0. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-32B-Instruct"}. This record does not assert independent reproduction. ### SGPO Pass@1: 53.81. Result ID: 69b11fe66dbb7075b95b4da2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-32B-Instruct","Judge Model":"o4-mini-0416"}. This record does not assert independent reproduction. ### SGPO Pass@1: 53.33. Result ID: 69b11fe66dbb7075b95b4d9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B-Instruct","Judge Model":"o4-mini-0416"}. This record does not assert independent reproduction. ### GRPO Pass@1: 52.86. Result ID: 69b11fe66dbb7075b95b4da1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-32B-Instruct"}. This record does not assert independent reproduction. ### Baseline Pass@1: 49.52. Result ID: 69b11fe66dbb7075b95b4d9d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### SGPO Pass@1: 47.17. Result ID: 69b11fe66dbb7075b95b4d96. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B","Judge Model":"DeepSeek-V3-0324"}. This record does not assert independent reproduction. ### GRPO Pass@1: 47.14. Result ID: 69b11fe66dbb7075b95b4d9e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-14B-Instruct"}. This record does not assert independent reproduction. ### SGPO Pass@1: 46.67. Result ID: 69b11fe66dbb7075b95b4d97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B","Judge Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction. ### SGPO Pass@1: 46.19. Result ID: 69b11fe66dbb7075b95b4d95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B","Judge Model":"o4-mini-0416"}. This record does not assert independent reproduction. ### SGPO Pass@1: 45.24. Result ID: 69b11fe66dbb7075b95b4d98. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B","Judge Model":"QwQ-32B"}. This record does not assert independent reproduction. ### GRPO Pass@1: 43.33. Result ID: 69b11fe66dbb7075b95b4d94. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### SGPO Pass@1: 42.38. Result ID: 69b11fe66dbb7075b95b4d99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B","Judge Model":"QwQ-32B","Stability Parameters":"w/o {beta,gamma}"}. This record does not assert independent reproduction. ### Baseline Pass@1: 41.43. Result ID: 69b11fe66dbb7075b95b4d93. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### SGPO Pass@1: 29.05. Result ID: 69b11fe66dbb7075b95b4d9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Llama-8B","Judge Model":"Claude-3.7"}. This record does not assert independent reproduction. ### GRPO Pass@1: 28.33. Result ID: 69b11fe66dbb7075b95b4d9b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Llama-8B"}. This record does not assert independent reproduction. ### Baseline Pass@1: 23.81. Result ID: 69b11fe66dbb7075b95b4d9a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Llama-8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.