# Mathematical Reasoning on AMC23 (Avg@32) Source: [Mathematical Reasoning on AMC23 (Avg@32)]() Collection index: [llms.txt]() Data updated: 2026-04-16T08:43:35.510Z Evaluation of model performance on the AMC23 dataset for Mathematical Reasoning tasks, specifically measured using the Avg@32 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) | AMC23 | | Metric | Avg@32 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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@32](): Higher is better; unit: PERCENT. ## Recorded results | Method | Avg@32 | Result date | Report paper | | --- | --- | --- | --- | | DSRL | 90 | Not recorded | 69e06d377d0172140ec7cca5 | | PPO | 89.69 | Not recorded | 69e06d377d0172140ec7cca5 | | DSRL | 89.22 | Not recorded | 69e06d377d0172140ec7cca5 | | DAPO | 88.52 | Not recorded | 69e06d377d0172140ec7cca5 | | DAPO | 88.2 | Not recorded | 69e06d377d0172140ec7cca5 | | GRPO | 88.05 | Not recorded | 69e06d377d0172140ec7cca5 | | PPO | 87.89 | Not recorded | 69e06d377d0172140ec7cca5 | | GRPO | 87.81 | Not recorded | 69e06d377d0172140ec7cca5 | | Dr.GRPO | 87.66 | Not recorded | 69e06d377d0172140ec7cca5 | | Dr.GRPO | 87.58 | Not recorded | 69e06d377d0172140ec7cca5 | | RLOO | 87.27 | Not recorded | 69e06d377d0172140ec7cca5 | | RLOO | 85 | Not recorded | 69e06d377d0172140ec7cca5 | | Reinforce++ | 84.14 | Not recorded | 69e06d377d0172140ec7cca5 | | Reinforce++ | 79.37 | Not recorded | 69e06d377d0172140ec7cca5 | | Vanilla | 69.53 | Not recorded | 69e06d377d0172140ec7cca5 | | Vanilla | 68.28 | Not recorded | 69e06d377d0172140ec7cca5 | ### DSRL Avg@32: 90. Result ID: 69e0a0d347f34ce924c9ef51. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### PPO Avg@32: 89.69. Result ID: 69e0a0d347f34ce924c9ef4b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### DSRL Avg@32: 89.22. Result ID: 69e0a0d347f34ce924c9ef49. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### DAPO Avg@32: 88.52. Result ID: 69e0a0d347f34ce924c9ef4f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### DAPO Avg@32: 88.2. Result ID: 69e0a0d347f34ce924c9ef47. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### GRPO Avg@32: 88.05. Result ID: 69e0a0d347f34ce924c9ef50. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### PPO Avg@32: 87.89. Result ID: 69e0a0d347f34ce924c9ef43. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### GRPO Avg@32: 87.81. Result ID: 69e0a0d347f34ce924c9ef48. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### Dr.GRPO Avg@32: 87.66. Result ID: 69e0a0d347f34ce924c9ef4e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Dr.GRPO Avg@32: 87.58. Result ID: 69e0a0d347f34ce924c9ef46. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### RLOO Avg@32: 87.27. Result ID: 69e0a0d347f34ce924c9ef4d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### RLOO Avg@32: 85. Result ID: 69e0a0d347f34ce924c9ef45. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### Reinforce++ Avg@32: 84.14. Result ID: 69e0a0d347f34ce924c9ef4c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Reinforce++ Avg@32: 79.37. Result ID: 69e0a0d347f34ce924c9ef44. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. ### Vanilla Avg@32: 69.53. Result ID: 69e0a0d347f34ce924c9ef4a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-8B"}. This record does not assert independent reproduction. ### Vanilla Avg@32: 68.28. Result ID: 69e0a0d347f34ce924c9ef42. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.