# Competitive Mathematical Reasoning on AMC 2023 (Pass@1) Source: [Competitive Mathematical Reasoning on AMC 2023 (Pass@1)]() Collection index: [llms.txt]() Data updated: 2026-06-09T10:04:07.670Z Evaluation of model performance on the AMC 2023 dataset for competitive mathematical reasoning, specifically measured using the Pass@1 accuracy 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 | Competitive Mathematical Reasoning | | Dataset (including any stated split) | AMC 2023 | | Metric | Pass@1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 37 of 37 | | 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 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pass@1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Qwen3-max | 100 | Not recorded | 6a279e7c90966ade919bfbd0 | | DeepSeek-V4-pro | 100 | Not recorded | 6a279e7c90966ade919bfbd0 | | GPT-5(high) | 97.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | DeepSeek-R1-Distill-Qwen-32B | 97.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | DiScOw/o ITDE | 97.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | DiScO | 97.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | DiScO | 92.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | Qwen3-32B | 92.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | DeepSeek-R1-Distill-Qwen-7B | 87.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | rStar-Math-7B | 87.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | DiScOw/o ITDE | 87.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | GPT-o1-mini | 85 | Not recorded | 6a279e7c90966ade919bfbd0 | | GPT-o1-preview | 85 | Not recorded | 6a279e7c90966ade919bfbd0 | | ReasonFlux-32B | 85 | Not recorded | 6a279e7c90966ade919bfbd0 | | Sky-T1-32B-preview | 82.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | Claude3.5-Sonnet | 80 | Not recorded | 6a279e7c90966ade919bfbd0 | | DeepSeek-V3 | 80 | Not recorded | 6a279e7c90966ade919bfbd0 | | ReasonFlux-7B | 80 | Not recorded | 6a279e7c90966ade919bfbd0 | | QwQ-32B-preview | 75 | Not recorded | 6a279e7c90966ade919bfbd0 | | NuminaMath-72B-CoT | 70 | Not recorded | 6a279e7c90966ade919bfbd0 | | Qwen2.5-Math-72B-Instruct | 70 | Not recorded | 6a279e7c90966ade919bfbd0 | | Qwen3-8B | 65 | Not recorded | 6a279e7c90966ade919bfbd0 | | DeepSeek-R1 | 64.1 | Not recorded | 6a279e7c90966ade919bfbd0 | | Qwen2.5-32B-Instruct | 64 | Not recorded | 6a279e7c90966ade919bfbd0 | | DIVER | 62.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | DeepSeek-Coder-V2-Instruct | 57.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | Entropy-RL | 57.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | GRPO w/ Clip-higher | 57.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | Pass@k Training | 52.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | LLaMA3.1-70B-Instruct | 50 | Not recorded | 6a279e7c90966ade919bfbd0 | | LLaMA3.1-405B-Instruct | 50 | Not recorded | 6a279e7c90966ade919bfbd0 | | GPT-4o | 47.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | Mathstral-7B-v0.1 | 37.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | SuperCorrect-7B | 37.5 | Not recorded | 6a279e7c90966ade919bfbd0 | | Qwen2.5-Math-7B-Instruct | 28.3 | Not recorded | 6a279e7c90966ade919bfbd0 | | LLaMA3.1-8B-Instruct | 25 | Not recorded | 6a279e7c90966ade919bfbd0 | | Qwen2.5-Math-7B | 22.5 | Not recorded | 6a279e7c90966ade919bfbd0 | ### Qwen3-max Pass@1 Accuracy: 100. Result ID: 6a27e45dfbc373592c25304c. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Closed-source frontier"}. This record does not assert independent reproduction. ### DeepSeek-V4-pro Pass@1 Accuracy: 100. Result ID: 6a27e45dfbc373592c253055. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Open-source frontier"}. This record does not assert independent reproduction. ### GPT-5(high) Pass@1 Accuracy: 97.5. Result ID: 6a27e45dfbc373592c25304d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Closed-source frontier"}. This record does not assert independent reproduction. ### DeepSeek-R1-Distill-Qwen-32B Pass@1 Accuracy: 97.5. Result ID: 6a27e45dfbc373592c253069. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"32B","Model Category":"Reasoning-specialized models"}. This record does not assert independent reproduction. ### DiScOw/o ITDE Pass@1 Accuracy: 97.5. Result ID: 6a27e45dfbc373592c25306b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"32B","Model Category":"Ours"}. This record does not assert independent reproduction. ### DiScO Pass@1 Accuracy: 97.5. Result ID: 6a27e45dfbc373592c25306c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"32B","Model Category":"Ours"}. This record does not assert independent reproduction. ### DiScO Pass@1 Accuracy: 92.5. Result ID: 6a27e45dfbc373592c253064. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"Ours"}. This record does not assert independent reproduction. ### Qwen3-32B Pass@1 Accuracy: 92.5. Result ID: 6a27e45dfbc373592c25306a. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"32B","Model Category":"Reasoning-specialized models"}. This record does not assert independent reproduction. ### DeepSeek-R1-Distill-Qwen-7B Pass@1 Accuracy: 87.5. Result ID: 6a27e45dfbc373592c25305b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"Reasoning-specialized models"}. This record does not assert independent reproduction. ### rStar-Math-7B Pass@1 Accuracy: 87.5. Result ID: 6a27e45dfbc373592c25305e. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"Reasoning-specialized models"}. This record does not assert independent reproduction. ### DiScOw/o ITDE Pass@1 Accuracy: 87.5. Result ID: 6a27e45dfbc373592c253063. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"Ours"}. This record does not assert independent reproduction. ### GPT-o1-mini Pass@1 Accuracy: 85. Result ID: 6a27e45dfbc373592c25304a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Closed-source frontier"}. This record does not assert independent reproduction. ### GPT-o1-preview Pass@1 Accuracy: 85. Result ID: 6a27e45dfbc373592c25304b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Closed-source frontier"}. This record does not assert independent reproduction. ### ReasonFlux-32B Pass@1 Accuracy: 85. Result ID: 6a27e45dfbc373592c253067. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"32B","Model Category":"Reasoning-specialized models"}. This record does not assert independent reproduction. ### Sky-T1-32B-preview Pass@1 Accuracy: 82.5. Result ID: 6a27e45dfbc373592c253066. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"32B","Model Category":"Reasoning-specialized models"}. This record does not assert independent reproduction. ### Claude3.5-Sonnet Pass@1 Accuracy: 80. Result ID: 6a27e45dfbc373592c253049. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Closed-source frontier"}. This record does not assert independent reproduction. ### DeepSeek-V3 Pass@1 Accuracy: 80. Result ID: 6a27e45dfbc373592c253053. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Open-source frontier"}. This record does not assert independent reproduction. ### ReasonFlux-7B Pass@1 Accuracy: 80. Result ID: 6a27e45dfbc373592c25305c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"Reasoning-specialized models"}. This record does not assert independent reproduction. ### QwQ-32B-preview Pass@1 Accuracy: 75. Result ID: 6a27e45dfbc373592c253068. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"32B","Model Category":"Reasoning-specialized models"}. This record does not assert independent reproduction. ### NuminaMath-72B-CoT Pass@1 Accuracy: 70. Result ID: 6a27e45dfbc373592c25304e. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Open-source frontier"}. This record does not assert independent reproduction. ### Qwen2.5-Math-72B-Instruct Pass@1 Accuracy: 70. Result ID: 6a27e45dfbc373592c253052. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Open-source frontier"}. This record does not assert independent reproduction. ### Qwen3-8B Pass@1 Accuracy: 65. Result ID: 6a27e45dfbc373592c25305d. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"Reasoning-specialized models"}. This record does not assert independent reproduction. ### DeepSeek-R1 Pass@1 Accuracy: 64.1. Result ID: 6a27e45dfbc373592c253054. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Open-source frontier"}. This record does not assert independent reproduction. ### Qwen2.5-32B-Instruct Pass@1 Accuracy: 64. Result ID: 6a27e45dfbc373592c253065. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"32B","Model Category":"Instruction-tuned models"}. This record does not assert independent reproduction. ### DIVER Pass@1 Accuracy: 62.5. Result ID: 6a27e45dfbc373592c253062. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"Diversity-oriented RL models"}. This record does not assert independent reproduction. ### DeepSeek-Coder-V2-Instruct Pass@1 Accuracy: 57.5. Result ID: 6a27e45dfbc373592c253050. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Open-source frontier"}. This record does not assert independent reproduction. ### Entropy-RL Pass@1 Accuracy: 57.5. Result ID: 6a27e45dfbc373592c25305f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"Diversity-oriented RL models"}. This record does not assert independent reproduction. ### GRPO w/ Clip-higher Pass@1 Accuracy: 57.5. Result ID: 6a27e45dfbc373592c253060. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"Diversity-oriented RL models"}. This record does not assert independent reproduction. ### Pass@k Training Pass@1 Accuracy: 52.5. Result ID: 6a27e45dfbc373592c253061. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"Diversity-oriented RL models"}. This record does not assert independent reproduction. ### LLaMA3.1-70B-Instruct Pass@1 Accuracy: 50. Result ID: 6a27e45dfbc373592c25304f. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Open-source frontier"}. This record does not assert independent reproduction. ### LLaMA3.1-405B-Instruct Pass@1 Accuracy: 50. Result ID: 6a27e45dfbc373592c253051. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Open-source frontier"}. This record does not assert independent reproduction. ### GPT-4o Pass@1 Accuracy: 47.5. Result ID: 6a27e45dfbc373592c253048. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Reference","Model Category":"Closed-source frontier"}. This record does not assert independent reproduction. ### Mathstral-7B-v0.1 Pass@1 Accuracy: 37.5. Result ID: 6a27e45dfbc373592c253057. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"General instruction-tuned models"}. This record does not assert independent reproduction. ### SuperCorrect-7B Pass@1 Accuracy: 37.5. Result ID: 6a27e45dfbc373592c25305a. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"Reasoning-specialized models"}. This record does not assert independent reproduction. ### Qwen2.5-Math-7B-Instruct Pass@1 Accuracy: 28.3. Result ID: 6a27e45dfbc373592c253059. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"Math instruction-tuned models"}. This record does not assert independent reproduction. ### LLaMA3.1-8B-Instruct Pass@1 Accuracy: 25. Result ID: 6a27e45dfbc373592c253056. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"General instruction-tuned models"}. This record does not assert independent reproduction. ### Qwen2.5-Math-7B Pass@1 Accuracy: 22.5. Result ID: 6a27e45dfbc373592c253058. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"7B","Model Category":"Math instruction-tuned models"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.