# Mathematical Problem Solving on AIME 2026 (Score %) Source: [Mathematical Problem Solving on AIME 2026 (Score %)]() Collection index: [llms.txt]() Data updated: 2026-07-02T08:11:10.025Z Evaluation of model performance on the AIME 2026 dataset for mathematical problem solving, measured by Score percentage. 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 Problem Solving | | Dataset (including any stated split) | AIME 2026 | | Metric | AIME 2026 Score | | Unit | PERCENT | | 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 - [AIME 2026 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | AIME 2026 Score | Result date | Report paper | | --- | --- | --- | --- | | STAR-PólyaMath | 100 | Not recorded | 6a0d4002f984739ed6737770 | | GPT-5.4 | 99.17 | Not recorded | 6a0d4002f984739ed6737770 | | GPT-5.2 | 98.33 | Not recorded | 6a0d4002f984739ed6737770 | | Gemini 3.1 Pro | 98.33 | Not recorded | 6a0d4002f984739ed6737770 | | GPT-5.5 | 97.5 | Not recorded | 6a0d4002f984739ed6737770 | | Claude Opus 4.6 | 96.67 | Not recorded | 6a0d4002f984739ed6737770 | | Claude Opus 4.7 | 95.83 | Not recorded | 6a0d4002f984739ed6737770 | | DeepSeek-v4-Pro | 95.83 | Not recorded | 6a0d4002f984739ed6737770 | | Kimi K2.6 | 95.83 | Not recorded | 6a0d4002f984739ed6737770 | | Kimi K2.5 | 95.83 | Not recorded | 6a0d4002f984739ed6737770 | | GLM 5.1 | 95.83 | Not recorded | 6a0d4002f984739ed6737770 | | Gemini-3-Flash | 93.3 | Not recorded | 6a45f082dc71372d7795a1ae | | GPT-5-mini | 92.5 | Not recorded | 6a45f082dc71372d7795a1ae | | Gemini 3 Pro | 91.67 | Not recorded | 6a0d4002f984739ed6737770 | | Seed2.0 Lite | 88.3 | Not recorded | 6a45f082dc71372d7795a1ae | | Seed2.0 Mini | 86.7 | Not recorded | 6a45f082dc71372d7795a1ae | ### STAR-PólyaMath AIME 2026 Score: 100. Result ID: 6a0d6a09fbc373592c0546d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"all GPT-5.5xh"}. This record does not assert independent reproduction. ### GPT-5.4 AIME 2026 Score: 99.17. Result ID: 6a0d6a09fbc373592c0546c9. [Reporting paper]() Recorded evaluation configuration: {"Reasoning Effort":"xhigh"}. This record does not assert independent reproduction. ### GPT-5.2 AIME 2026 Score: 98.33. Result ID: 6a0d6a09fbc373592c0546ca. [Reporting paper]() Recorded evaluation configuration: {"Reasoning Effort":"high"}. This record does not assert independent reproduction. ### Gemini 3.1 Pro AIME 2026 Score: 98.33. Result ID: 6a0d6a09fbc373592c0546cb. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5.5 AIME 2026 Score: 97.5. Result ID: 6a0d6a09fbc373592c0546c8. [Reporting paper]() Recorded evaluation configuration: {"Reasoning Effort":"xhigh"}. This record does not assert independent reproduction. ### Claude Opus 4.6 AIME 2026 Score: 96.67. Result ID: 6a0d6a09fbc373592c0546ce. [Reporting paper]() Recorded evaluation configuration: {"Reasoning Effort":"high"}. This record does not assert independent reproduction. ### Claude Opus 4.7 AIME 2026 Score: 95.83. Result ID: 6a0d6a09fbc373592c0546cd. [Reporting paper]() Recorded evaluation configuration: {"Reasoning Effort":"xhigh"}. This record does not assert independent reproduction. ### DeepSeek-v4-Pro AIME 2026 Score: 95.83. Result ID: 6a0d6a09fbc373592c0546cf. [Reporting paper]() Recorded evaluation configuration: {"Reasoning Effort":"Max"}. This record does not assert independent reproduction. ### Kimi K2.6 AIME 2026 Score: 95.83. Result ID: 6a0d6a09fbc373592c0546d0. [Reporting paper]() Recorded evaluation configuration: {"Reasoning Effort":"Think"}. This record does not assert independent reproduction. ### Kimi K2.5 AIME 2026 Score: 95.83. Result ID: 6a0d6a09fbc373592c0546d1. [Reporting paper]() Recorded evaluation configuration: {"Reasoning Effort":"Think"}. This record does not assert independent reproduction. ### GLM 5.1 AIME 2026 Score: 95.83. Result ID: 6a0d6a09fbc373592c0546d2. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini-3-Flash AIME 2026 Score: 93.3. Result ID: 6a461cfe60b88bb33984aa26. [Reporting paper]() Recorded evaluation configuration: {"Tier":"High"}. This record does not assert independent reproduction. ### GPT-5-mini AIME 2026 Score: 92.5. Result ID: 6a461cfe60b88bb33984aa25. [Reporting paper]() Recorded evaluation configuration: {"Tier":"High"}. This record does not assert independent reproduction. ### Gemini 3 Pro AIME 2026 Score: 91.67. Result ID: 6a0d6a09fbc373592c0546cc. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Seed2.0 Lite AIME 2026 Score: 88.3. Result ID: 6a461cfe60b88bb33984aa28. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Seed2.0 Mini AIME 2026 Score: 86.7. Result ID: 6a461cfe60b88bb33984aa27. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.