AIME 2025
- OpenAI
Results
| Model | Score | Source | Human-verified |
|---|---|---|---|
| GPT-57 Aug 2025 · OpenAI | 99.6% | Introducing GPT-5Read from the full-page screenshot (shots.jsonl part 3, image 97; the bar's x-axis label is at the top of part 4, kb:/api/images/98, sha256 f036431e418305f0b45d54e5179176b075413da4a646a81867a80b28bd140ddb). Chart y-axis 'Accuracy, pass@1'; legend: dark = With thinking, light = Without thinking; stacked bar, value label on each segment. Footnote under the chart: '*AIME results with tools should not be compared directly to the performance of models without tool access; they are an example of how effectively GPT-5 leverages available tools.' Tool: Python. Read from a full-page screenshot of the post (para-kb image /api/images/97), as openai.com is bot-walled. | Yes |
| GPT-57 Aug 2025 · OpenAI | 71.0% | Introducing GPT-5another report, not charted; Read from the full-page screenshot (shots.jsonl part 3, image 97; the bar's x-axis label is at the top of part 4, kb:/api/images/98, sha256 f036431e418305f0b45d54e5179176b075413da4a646a81867a80b28bd140ddb). Chart y-axis 'Accuracy, pass@1'; legend: dark = With thinking, light = Without thinking; stacked bar, value label on each segment. Footnote under the chart: '*AIME results with tools should not be compared directly to the performance of models without tool access; they are an example of how effectively GPT-5 leverages available tools.' Tool: Python. Without-thinking value. Read from a full-page screenshot of the post (para-kb image /api/images/97), as openai.com is bot-walled. | Yes |
| OpenAI o316 Apr 2025 · OpenAI | 98.4% | Introducing OpenAI o3 and o4-miniSentence in the text; tool is a Python interpreter (the sentence compares to o4-mini 'when given access to a Python interpreter'). pass@1. The post says these with-tools results should not be compared to models without tool access. | Yes |
| OpenAI o316 Apr 2025 · OpenAI | 100% | Introducing OpenAI o3 and o4-miniparallel test-time compute; consensus@8 (majority voting over 8 samples), with a Python interpreter. | Yes |
Benchmark
maa.orgHigher is better
Mathematical Association of AmericaIntroduced 12 Feb 2025