# Mathematical Reasoning on AIME 2024 (VeRA-E) Source: [Mathematical Reasoning on AIME 2024 (VeRA-E)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:04:09.713Z Evaluation of model performance on the American Invitational Mathematics Examination (AIME) 2024 dataset, reporting results using VeRA-E and Delta (∆) 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) | AIME 2024 | | Metric | Seed | | 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 - [Seed](): Higher is better; unit: SCALAR. - [VeRA-E](): Higher is better; unit: PERCENT. - [Delta (∆)](): Lower is better; unit: SCALAR. ## Recorded results | Method | Seed | Result date | Report paper | | --- | --- | --- | --- | | Gemini-3-Pro-Preview | 94 | Not recorded | 6993f6229ebc499c97409b26 | | GPT-5.1-high | 92 | Not recorded | 6993f6229ebc499c97409b26 | | DeepSeek-V3.2-thinking | 92 | Not recorded | 6993f6229ebc499c97409b26 | | GLM-4.6 | 90.7 | Not recorded | 6993f6229ebc499c97409b26 | | DeepSeek-V3.1-thinking | 90.7 | Not recorded | 6993f6229ebc499c97409b26 | | GPT-5-high | 90 | Not recorded | 6993f6229ebc499c97409b26 | | Seed-1.6-1015-high | 89.3 | Not recorded | 6993f6229ebc499c97409b26 | | Gemini-2.5-Pro | 88 | Not recorded | 6993f6229ebc499c97409b26 | | Seed-1.6-Lite-1015-high | 87.3 | Not recorded | 6993f6229ebc499c97409b26 | | Kimi-K2-thinking | 86.7 | Not recorded | 6993f6229ebc499c97409b26 | | Seed-1.6-Thinking-0715 | 85.3 | Not recorded | 6993f6229ebc499c97409b26 | | Minimax-M2 | 84.7 | Not recorded | 6993f6229ebc499c97409b26 | | Claude-Sonnet-4.5-thinking | 84 | Not recorded | 6993f6229ebc499c97409b26 | | qwen3-max-0923 | 82.7 | Not recorded | 6993f6229ebc499c97409b26 | | Kimi-K2-0905 | 65.3 | Not recorded | 6993f6229ebc499c97409b26 | | GPT-5.1-chat-latest | 48.7 | Not recorded | 6993f6229ebc499c97409b26 | ### Gemini-3-Pro-Preview Seed: 94. Result ID: 699a6b615698665ec4f3d79a. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### GPT-5.1-high Seed: 92. Result ID: 699a6b615698665ec4f3d793. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### DeepSeek-V3.2-thinking Seed: 92. Result ID: 699a6b615698665ec4f3d796. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### GLM-4.6 Seed: 90.7. Result ID: 699a6b615698665ec4f3d792. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### DeepSeek-V3.1-thinking Seed: 90.7. Result ID: 699a6b615698665ec4f3d7a0. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### GPT-5-high Seed: 90. Result ID: 699a6b615698665ec4f3d79b. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### Seed-1.6-1015-high Seed: 89.3. Result ID: 699a6b615698665ec4f3d797. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### Gemini-2.5-Pro Seed: 88. Result ID: 699a6b615698665ec4f3d791. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### Seed-1.6-Lite-1015-high Seed: 87.3. Result ID: 699a6b615698665ec4f3d79f. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### Kimi-K2-thinking Seed: 86.7. Result ID: 699a6b615698665ec4f3d798. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### Seed-1.6-Thinking-0715 Seed: 85.3. Result ID: 699a6b615698665ec4f3d795. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### Minimax-M2 Seed: 84.7. Result ID: 699a6b615698665ec4f3d799. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### Claude-Sonnet-4.5-thinking Seed: 84. Result ID: 699a6b615698665ec4f3d794. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### qwen3-max-0923 Seed: 82.7. Result ID: 699a6b615698665ec4f3d79d. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### Kimi-K2-0905 Seed: 65.3. Result ID: 699a6b615698665ec4f3d79c. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. ### GPT-5.1-chat-latest Seed: 48.7. Result ID: 699a6b615698665ec4f3d79e. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Avg@5 (%)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.