# Mathematical Reasoning on AIME 2025 (Avg@5) Source: [Mathematical Reasoning on AIME 2025 (Avg@5)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:36:32.883Z Evaluation of model performance on the American Invitational Mathematics Examination (AIME) 2025 dataset, specifically measured using the Avg@5 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 2025 | | Metric | Avg@5 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 32 of 32 | | 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@5 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Avg@5 Score | Result date | Report paper | | --- | --- | --- | --- | | GLM-4.6 | 92 | Not recorded | 6993f6229ebc499c97409b26 | | Gemini-3-Pro-Preview | 90.7 | Not recorded | 6993f6229ebc499c97409b26 | | DeepSeek-V3.2-thinking | 90 | Not recorded | 6993f6229ebc499c97409b26 | | GPT-5-high | 89.3 | Not recorded | 6993f6229ebc499c97409b26 | | GPT-5.1-high | 88.7 | Not recorded | 6993f6229ebc499c97409b26 | | GPT-5.1-high | 88.3 | Not recorded | 6993f6229ebc499c97409b26 | | DeepSeek-V3.2-thinking | 87.7 | Not recorded | 6993f6229ebc499c97409b26 | | DeepSeek-V3.1-thinking | 86.7 | Not recorded | 6993f6229ebc499c97409b26 | | Gemini-3-Pro-Preview | 85.7 | Not recorded | 6993f6229ebc499c97409b26 | | Gemini-2.5-Pro | 85.3 | Not recorded | 6993f6229ebc499c97409b26 | | GPT-5-high | 85.3 | Not recorded | 6993f6229ebc499c97409b26 | | DeepSeek-V3.1-thinking | 83 | Not recorded | 6993f6229ebc499c97409b26 | | Seed-1.6-1015-high | 80.7 | Not recorded | 6993f6229ebc499c97409b26 | | Seed-1.6-Thinking-0715 | 80 | Not recorded | 6993f6229ebc499c97409b26 | | Claude-Sonnet-4.5-thinking | 78.7 | Not recorded | 6993f6229ebc499c97409b26 | | Kimi-K2-thinking | 78.7 | Not recorded | 6993f6229ebc499c97409b26 | | Seed-1.6-Lite-1015-high | 77.3 | Not recorded | 6993f6229ebc499c97409b26 | | Seed-1.6-1015-high | 76.7 | Not recorded | 6993f6229ebc499c97409b26 | | Minimax-M2 | 76.7 | Not recorded | 6993f6229ebc499c97409b26 | | GLM-4.6 | 76.3 | Not recorded | 6993f6229ebc499c97409b26 | | Seed-1.6-Thinking-0715 | 75.3 | Not recorded | 6993f6229ebc499c97409b26 | | qwen3-max-0923 | 74.7 | Not recorded | 6993f6229ebc499c97409b26 | | Gemini-2.5-Pro | 73 | Not recorded | 6993f6229ebc499c97409b26 | | Kimi-K2-thinking | 71.7 | Not recorded | 6993f6229ebc499c97409b26 | | Seed-1.6-Lite-1015-high | 70 | Not recorded | 6993f6229ebc499c97409b26 | | qwen3-max-0923 | 69.7 | Not recorded | 6993f6229ebc499c97409b26 | | Claude-Sonnet-4.5-thinking | 68.7 | Not recorded | 6993f6229ebc499c97409b26 | | Minimax-M2 | 57 | Not recorded | 6993f6229ebc499c97409b26 | | GPT-5.1-chat-latest | 50.7 | Not recorded | 6993f6229ebc499c97409b26 | | Kimi-K2-0905 | 47.3 | Not recorded | 6993f6229ebc499c97409b26 | | Kimi-K2-0905 | 44 | Not recorded | 6993f6229ebc499c97409b26 | | GPT-5.1-chat-latest | 41.7 | Not recorded | 6993f6229ebc499c97409b26 | ### GLM-4.6 Avg@5 Score: 92. Result ID: 699a6b615698665ec4f3d6cf. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### Gemini-3-Pro-Preview Avg@5 Score: 90.7. Result ID: 699a6b615698665ec4f3d6df. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### DeepSeek-V3.2-thinking Avg@5 Score: 90. Result ID: 699a6b615698665ec4f3d6d7. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### GPT-5-high Avg@5 Score: 89.3. Result ID: 699a6b615698665ec4f3d6e1. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### GPT-5.1-high Avg@5 Score: 88.7. Result ID: 699a6b615698665ec4f3d6d1. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### GPT-5.1-high Avg@5 Score: 88.3. Result ID: 699a6b615698665ec4f3d6d2. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### DeepSeek-V3.2-thinking Avg@5 Score: 87.7. Result ID: 699a6b615698665ec4f3d6d8. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### DeepSeek-V3.1-thinking Avg@5 Score: 86.7. Result ID: 699a6b615698665ec4f3d6eb. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### Gemini-3-Pro-Preview Avg@5 Score: 85.7. Result ID: 699a6b615698665ec4f3d6e0. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Avg@5 Score: 85.3. Result ID: 699a6b615698665ec4f3d6cd. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### GPT-5-high Avg@5 Score: 85.3. Result ID: 699a6b615698665ec4f3d6e2. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### DeepSeek-V3.1-thinking Avg@5 Score: 83. Result ID: 699a6b615698665ec4f3d6ec. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### Seed-1.6-1015-high Avg@5 Score: 80.7. Result ID: 699a6b615698665ec4f3d6d9. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### Seed-1.6-Thinking-0715 Avg@5 Score: 80. Result ID: 699a6b615698665ec4f3d6d5. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### Claude-Sonnet-4.5-thinking Avg@5 Score: 78.7. Result ID: 699a6b615698665ec4f3d6d3. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### Kimi-K2-thinking Avg@5 Score: 78.7. Result ID: 699a6b615698665ec4f3d6db. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### Seed-1.6-Lite-1015-high Avg@5 Score: 77.3. Result ID: 699a6b615698665ec4f3d6e9. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### Seed-1.6-1015-high Avg@5 Score: 76.7. Result ID: 699a6b615698665ec4f3d6da. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### Minimax-M2 Avg@5 Score: 76.7. Result ID: 699a6b615698665ec4f3d6dd. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### GLM-4.6 Avg@5 Score: 76.3. Result ID: 699a6b615698665ec4f3d6d0. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### Seed-1.6-Thinking-0715 Avg@5 Score: 75.3. Result ID: 699a6b615698665ec4f3d6d6. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### qwen3-max-0923 Avg@5 Score: 74.7. Result ID: 699a6b615698665ec4f3d6e5. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Avg@5 Score: 73. Result ID: 699a6b615698665ec4f3d6ce. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### Kimi-K2-thinking Avg@5 Score: 71.7. Result ID: 699a6b615698665ec4f3d6dc. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### Seed-1.6-Lite-1015-high Avg@5 Score: 70. Result ID: 699a6b615698665ec4f3d6ea. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### qwen3-max-0923 Avg@5 Score: 69.7. Result ID: 699a6b615698665ec4f3d6e6. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### Claude-Sonnet-4.5-thinking Avg@5 Score: 68.7. Result ID: 699a6b615698665ec4f3d6d4. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### Minimax-M2 Avg@5 Score: 57. Result ID: 699a6b615698665ec4f3d6de. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### GPT-5.1-chat-latest Avg@5 Score: 50.7. Result ID: 699a6b615698665ec4f3d6e7. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### Kimi-K2-0905 Avg@5 Score: 47.3. Result ID: 699a6b615698665ec4f3d6e3. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"seeds","Sample Count":30}. This record does not assert independent reproduction. ### Kimi-K2-0905 Avg@5 Score: 44. Result ID: 699a6b615698665ec4f3d6e4. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. ### GPT-5.1-chat-latest Avg@5 Score: 41.7. Result ID: 699a6b615698665ec4f3d6e8. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Variant":"VeRA-E","Sample Count":60}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.