# Mathematical Reasoning on AMC 2023 (test) (Accuracy, Length, AE) Source: [Mathematical Reasoning on AMC 2023 (test) (Accuracy, Length, AE)]() Collection index: [llms.txt]() Data updated: 2026-05-22T08:31:03.807Z Evaluation of model performance on the test split of the AMC 2023 dataset for mathematical reasoning, reporting accuracy, output length, and answer error metrics. 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) | AMC2023 (test) | | Metric | Accuracy | | 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](): Higher is better; unit: PERCENT. - [Output Length](): Higher is better; unit: SCALAR. - [Answer Error (AE)](): Lower is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Training Efficient | 83.8 | Not recorded | 6a0fe2fdf984739ed6739c92 | | Training Efficient+CLORE | 83.5 | Not recorded | 6a0fe2fdf984739ed6739c92 | | GRPO+CLORE | 82.7 | Not recorded | 6a0fe2fdf984739ed6739c92 | | ThinkPrune+CLORE | 82.7 | Not recorded | 6a0fe2fdf984739ed6739c92 | | DAPO | 82.6 | Not recorded | 6a0fe2fdf984739ed6739c92 | | DAPO+CLORE | 82.3 | Not recorded | 6a0fe2fdf984739ed6739c92 | | GRPO | 81.9 | Not recorded | 6a0fe2fdf984739ed6739c92 | | ThinkPrune | 80 | Not recorded | 6a0fe2fdf984739ed6739c92 | | GRPO | 76.5 | Not recorded | 6a0fe2fdf984739ed6739c92 | | Base model (w/o training) | 75.9 | Not recorded | 6a0fe2fdf984739ed6739c92 | | DAPO+CLORE | 75.9 | Not recorded | 6a0fe2fdf984739ed6739c92 | | GRPO+CLORE | 73.4 | Not recorded | 6a0fe2fdf984739ed6739c92 | | ThinkPrune+CLORE | 72.8 | Not recorded | 6a0fe2fdf984739ed6739c92 | | ThinkPrune | 72.1 | Not recorded | 6a0fe2fdf984739ed6739c92 | | Training Efficient+CLORE | 64.5 | Not recorded | 6a0fe2fdf984739ed6739c92 | | Training Efficient | 63.8 | Not recorded | 6a0fe2fdf984739ed6739c92 | | DAPO | 56.1 | Not recorded | 6a0fe2fdf984739ed6739c92 | | Base model (w/o training) | 54.2 | Not recorded | 6a0fe2fdf984739ed6739c92 | ### Training Efficient Accuracy: 83.8. Result ID: 6a101441fbc373592c090fe7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### Training Efficient+CLORE Accuracy: 83.5. Result ID: 6a101441fbc373592c090fe8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### GRPO+CLORE Accuracy: 82.7. Result ID: 6a101441fbc373592c090fe4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### ThinkPrune+CLORE Accuracy: 82.7. Result ID: 6a101441fbc373592c090fea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### DAPO Accuracy: 82.6. Result ID: 6a101441fbc373592c090fe5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### DAPO+CLORE Accuracy: 82.3. Result ID: 6a101441fbc373592c090fe6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### GRPO Accuracy: 81.9. Result ID: 6a101441fbc373592c090fe3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### ThinkPrune Accuracy: 80. Result ID: 6a101441fbc373592c090fe9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### GRPO Accuracy: 76.5. Result ID: 6a101441fbc373592c090fec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction. ### Base model (w/o training) Accuracy: 75.9. Result ID: 6a101441fbc373592c090fe2. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### DAPO+CLORE Accuracy: 75.9. Result ID: 6a101441fbc373592c090fef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction. ### GRPO+CLORE Accuracy: 73.4. Result ID: 6a101441fbc373592c090fed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction. ### ThinkPrune+CLORE Accuracy: 72.8. Result ID: 6a101441fbc373592c090ff3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction. ### ThinkPrune Accuracy: 72.1. Result ID: 6a101441fbc373592c090ff2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction. ### Training Efficient+CLORE Accuracy: 64.5. Result ID: 6a101441fbc373592c090ff1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction. ### Training Efficient Accuracy: 63.8. Result ID: 6a101441fbc373592c090ff0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction. ### DAPO Accuracy: 56.1. Result ID: 6a101441fbc373592c090fee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction. ### Base model (w/o training) Accuracy: 54.2. Result ID: 6a101441fbc373592c090feb. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.