# Mathematical Reasoning on AIME (Acceptance length τ) Source: [Mathematical Reasoning on AIME (Acceptance length τ)]() Collection index: [llms.txt]() Data updated: 2026-06-11T06:15:29.650Z Evaluation of model performance on the American Invitational Mathematics Examination (AIME) dataset, specifically measuring the Acceptance length (τ) 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) | AIME | | Metric | Acceptance Length (τ) | | Unit | SCALAR | | 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 - [Acceptance Length (τ)](): Higher is better; unit: SCALAR. ## Recorded results | Method | Acceptance Length (τ) | Result date | Report paper | | --- | --- | --- | --- | | Llama-3-8B | 4.757 | Not recorded | 6a2a412ed33dfb23e78393bb | | Llama 3.2-3B | 4.197 | Not recorded | 6a2a412ed33dfb23e78393bb | | Llama-3-8B | 3.465 | Not recorded | 6a2a412ed33dfb23e78393bb | | Llama 3.2-3B | 3.455 | Not recorded | 6a2a412ed33dfb23e78393bb | | Llama 3.2-3B | 3.356 | Not recorded | 6a2a412ed33dfb23e78393bb | | Llama-3-8B | 3.152 | Not recorded | 6a2a412ed33dfb23e78393bb | | Llama 3.2-3B | 3.003 | Not recorded | 6a2a412ed33dfb23e78393bb | | Llama-3-8B | 2.705 | Not recorded | 6a2a412ed33dfb23e78393bb | | Qwen3-8B | 2.558 | Not recorded | 6a2a412ed33dfb23e78393bb | | Qwen3-4B | 2.554 | Not recorded | 6a2a412ed33dfb23e78393bb | | Qwen3-4B | 2.357 | Not recorded | 6a2a412ed33dfb23e78393bb | | Qwen3-8B | 2.351 | Not recorded | 6a2a412ed33dfb23e78393bb | | Qwen3-4B | 2.253 | Not recorded | 6a2a412ed33dfb23e78393bb | | Qwen3-8B | 2.233 | Not recorded | 6a2a412ed33dfb23e78393bb | | Qwen3-4B | 2.133 | Not recorded | 6a2a412ed33dfb23e78393bb | | Qwen3-8B | 2.03 | Not recorded | 6a2a412ed33dfb23e78393bb | ### Llama-3-8B Acceptance Length (τ): 4.757. Result ID: 6a2a527cfbc373592c269e87. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"10","αf (first-error focal coefficient)":"0.3","αc (chain-loss coefficient)":"40"}. This record does not assert independent reproduction. ### Llama 3.2-3B Acceptance Length (τ): 4.197. Result ID: 6a2a527cfbc373592c269e83. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"10","αf (first-error focal coefficient)":"0.3","αc (chain-loss coefficient)":"40"}. This record does not assert independent reproduction. ### Llama-3-8B Acceptance Length (τ): 3.465. Result ID: 6a2a527cfbc373592c269e86. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"10","αf (first-error focal coefficient)":"0.3","αc (chain-loss coefficient)":"0"}. This record does not assert independent reproduction. ### Llama 3.2-3B Acceptance Length (τ): 3.455. Result ID: 6a2a527cfbc373592c269e82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"10","αf (first-error focal coefficient)":"0.3","αc (chain-loss coefficient)":"0"}. This record does not assert independent reproduction. ### Llama 3.2-3B Acceptance Length (τ): 3.356. Result ID: 6a2a527cfbc373592c269e81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"10","αf (first-error focal coefficient)":"0","αc (chain-loss coefficient)":"0"}. This record does not assert independent reproduction. ### Llama-3-8B Acceptance Length (τ): 3.152. Result ID: 6a2a527cfbc373592c269e85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"10","αf (first-error focal coefficient)":"0","αc (chain-loss coefficient)":"0"}. This record does not assert independent reproduction. ### Llama 3.2-3B Acceptance Length (τ): 3.003. Result ID: 6a2a527cfbc373592c269e80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"None","αf (first-error focal coefficient)":"0","αc (chain-loss coefficient)":"0"}. This record does not assert independent reproduction. ### Llama-3-8B Acceptance Length (τ): 2.705. Result ID: 6a2a527cfbc373592c269e84. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"None","αf (first-error focal coefficient)":"0","αc (chain-loss coefficient)":"0"}. This record does not assert independent reproduction. ### Qwen3-8B Acceptance Length (τ): 2.558. Result ID: 6a2a527cfbc373592c269e8f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"10","αf (first-error focal coefficient)":"0.3","αc (chain-loss coefficient)":"40"}. This record does not assert independent reproduction. ### Qwen3-4B Acceptance Length (τ): 2.554. Result ID: 6a2a527cfbc373592c269e8b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"10","αf (first-error focal coefficient)":"0.3","αc (chain-loss coefficient)":"40"}. This record does not assert independent reproduction. ### Qwen3-4B Acceptance Length (τ): 2.357. Result ID: 6a2a527cfbc373592c269e8a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"10","αf (first-error focal coefficient)":"0.3","αc (chain-loss coefficient)":"0"}. This record does not assert independent reproduction. ### Qwen3-8B Acceptance Length (τ): 2.351. Result ID: 6a2a527cfbc373592c269e8e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"10","αf (first-error focal coefficient)":"0.3","αc (chain-loss coefficient)":"0"}. This record does not assert independent reproduction. ### Qwen3-4B Acceptance Length (τ): 2.253. Result ID: 6a2a527cfbc373592c269e89. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"10","αf (first-error focal coefficient)":"0","αc (chain-loss coefficient)":"0"}. This record does not assert independent reproduction. ### Qwen3-8B Acceptance Length (τ): 2.233. Result ID: 6a2a527cfbc373592c269e8d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"10","αf (first-error focal coefficient)":"0","αc (chain-loss coefficient)":"0"}. This record does not assert independent reproduction. ### Qwen3-4B Acceptance Length (τ): 2.133. Result ID: 6a2a527cfbc373592c269e88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"None","αf (first-error focal coefficient)":"0","αc (chain-loss coefficient)":"0"}. This record does not assert independent reproduction. ### Qwen3-8B Acceptance Length (τ): 2.03. Result ID: 6a2a527cfbc373592c269e8c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"γ (loss-decay constant)":"None","αf (first-error focal coefficient)":"0","αc (chain-loss coefficient)":"0"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.