# Mathematical Reasoning on AMC 23 (Acc, #Tok, LR) Source: [Mathematical Reasoning on AMC 23 (Acc, #Tok, LR)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:26:45.549Z Evaluation of model performance on the AMC 23 dataset for Mathematical Reasoning tasks, measured using Accuracy (Acc), Token Count (#Tok), and LR 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) | AMC 23 | | Metric | Acc | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 28 of 28 | | 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 - [Acc](): Higher is better; unit: PERCENT. - [#Tok](): Lower is better; unit: SCALAR. - [LR](): Higher is better; unit: OTHER. ## Recorded results | Method | Acc | Result date | Report paper | | --- | --- | --- | --- | | Vanilla | 93.3 | Not recorded | 6981819ea8b01e76cc8e2708 | | CGRS | 93.3 | Not recorded | 6981819ea8b01e76cc8e2708 | | NEAT | 93.3 | Not recorded | 6981819ea8b01e76cc8e2708 | | TALE | 92.5 | Not recorded | 6981819ea8b01e76cc8e2708 | | DEER | 90.8 | Not recorded | 6981819ea8b01e76cc8e2708 | | Dynasor | 90 | Not recorded | 6981819ea8b01e76cc8e2708 | | Vanilla | 89.4 | Not recorded | 6981819ea8b01e76cc8e2708 | | Dynasor | 89.2 | Not recorded | 6981819ea8b01e76cc8e2708 | | CGRS | 89.2 | Not recorded | 6981819ea8b01e76cc8e2708 | | DEER | 88.3 | Not recorded | 6981819ea8b01e76cc8e2708 | | CGRS | 88.3 | Not recorded | 6981819ea8b01e76cc8e2708 | | NEAT | 88.3 | Not recorded | 6981819ea8b01e76cc8e2708 | | TALE | 88.3 | Not recorded | 6981819ea8b01e76cc8e2708 | | NEAT | 88.3 | Not recorded | 6981819ea8b01e76cc8e2708 | | Vanilla | 87.5 | Not recorded | 6981819ea8b01e76cc8e2708 | | TALE | 86.7 | Not recorded | 6981819ea8b01e76cc8e2708 | | CGRS | 86.7 | Not recorded | 6981819ea8b01e76cc8e2708 | | NEAT | 85.6 | Not recorded | 6981819ea8b01e76cc8e2708 | | TALE | 85 | Not recorded | 6981819ea8b01e76cc8e2708 | | Dynasor | 84.2 | Not recorded | 6981819ea8b01e76cc8e2708 | | Vanilla | 84.2 | Not recorded | 6981819ea8b01e76cc8e2708 | | Dynasor | 84.2 | Not recorded | 6981819ea8b01e76cc8e2708 | | NoThinking | 82.5 | Not recorded | 6981819ea8b01e76cc8e2708 | | DEER | 80.8 | Not recorded | 6981819ea8b01e76cc8e2708 | | DEER | 79.2 | Not recorded | 6981819ea8b01e76cc8e2708 | | NoThinking | 77.5 | Not recorded | 6981819ea8b01e76cc8e2708 | | NoThinking | 75.8 | Not recorded | 6981819ea8b01e76cc8e2708 | | NoThinking | 72.5 | Not recorded | 6981819ea8b01e76cc8e2708 | ### Vanilla Acc: 93.3. Result ID: 699653955698665ec4989d79. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### CGRS Acc: 93.3. Result ID: 699653955698665ec4989d7e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### NEAT Acc: 93.3. Result ID: 699653955698665ec4989d7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### TALE Acc: 92.5. Result ID: 699653955698665ec4989d7b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### DEER Acc: 90.8. Result ID: 699653955698665ec4989d7d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### Dynasor Acc: 90. Result ID: 699653955698665ec4989d7c. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### Vanilla Acc: 89.4. Result ID: 699653955698665ec4989d72. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### Dynasor Acc: 89.2. Result ID: 699653955698665ec4989d75. [Reporting paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### CGRS Acc: 89.2. Result ID: 699653955698665ec4989d77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### DEER Acc: 88.3. Result ID: 699653955698665ec4989d68. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### CGRS Acc: 88.3. Result ID: 699653955698665ec4989d69. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### NEAT Acc: 88.3. Result ID: 699653955698665ec4989d6a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### TALE Acc: 88.3. Result ID: 699653955698665ec4989d74. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### NEAT Acc: 88.3. Result ID: 699653955698665ec4989d78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### Vanilla Acc: 87.5. Result ID: 699653955698665ec4989d64. [Reporting paper]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### TALE Acc: 86.7. Result ID: 699653955698665ec4989d66. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### CGRS Acc: 86.7. Result ID: 699653955698665ec4989d70. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Llama-8B"}. This record does not assert independent reproduction. ### NEAT Acc: 85.6. Result ID: 699653955698665ec4989d71. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Llama-8B"}. This record does not assert independent reproduction. ### TALE Acc: 85. Result ID: 699653955698665ec4989d6d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Llama-8B"}. This record does not assert independent reproduction. ### Dynasor Acc: 84.2. Result ID: 699653955698665ec4989d67. [Reporting paper]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### Vanilla Acc: 84.2. Result ID: 699653955698665ec4989d6b. [Reporting paper]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Llama-8B"}. This record does not assert independent reproduction. ### Dynasor Acc: 84.2. Result ID: 699653955698665ec4989d6e. [Reporting paper]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Llama-8B"}. This record does not assert independent reproduction. ### NoThinking Acc: 82.5. Result ID: 699653955698665ec4989d6c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Llama-8B"}. This record does not assert independent reproduction. ### DEER Acc: 80.8. Result ID: 699653955698665ec4989d6f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Llama-8B"}. This record does not assert independent reproduction. ### DEER Acc: 79.2. Result ID: 699653955698665ec4989d76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. ### NoThinking Acc: 77.5. Result ID: 699653955698665ec4989d7a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-14B"}. This record does not assert independent reproduction. ### NoThinking Acc: 75.8. Result ID: 699653955698665ec4989d65. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"DeepSeek-R1-Distill-Qwen-7B"}. This record does not assert independent reproduction. ### NoThinking Acc: 72.5. Result ID: 699653955698665ec4989d73. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3-8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.