AI Model Profile · OpenAI
GPT-4o
GPT-4o is an AI model developed by OpenAI (United States), released May 13, 2024. It is a closed model available via API.
Frontier model · API access · Epoch confidence: Speculative · Source: Epoch AI · Updated 2026-08-17
Specifications
| Developer | OpenAI |
| Country | United States |
| Released | May 13, 2024 |
| Domain | Multimodal,Language,Audio,Speech,Vision |
| Weights | Closed / API |
| Access | API access |
| Frontier model | Yes |
All figures from Epoch AI's Notable AI Models database (CC BY 4.0). Blank fields are undisclosed by the developer — never estimated by Affärslivet.
Benchmarks
Performance on Epoch AI's reproducible evaluations (higher is better; scores are the best across scorers). These are independent runs, not developer-reported numbers.
Source: Epoch AI Benchmarking Hub. GPQA Diamond = graduate-level science Q&A; SWE-Bench Verified = real software-engineering tasks; FrontierMath = research-level maths; MATH Level 5 = hardest competition maths; AIME = olympiad maths; SimpleQA = factual accuracy.
Frequently asked
- Who developed GPT-4o?
- GPT-4o was developed by OpenAI (United States) and released on May 13, 2024.
- Is GPT-4o open source?
- GPT-4o is a closed model — its weights are not publicly released; it is available via API access.
- How does GPT-4o perform on benchmarks?
- On Epoch AI's evaluations, GPT-4o scores 31.0% on SWE-Bench Verified, 0.3% on FrontierMath, 6.4% on AIME (OTIS Mock). Source: Epoch AI Benchmarking Hub.
Sources
Cite this model profile
Free to cite, quote and reference under CC BY 4.0 — with attribution to Affärslivet. Writing an article or answer? Reference this model profile as:
APA
Affärslivet Research. (2026). GPT-4o — specifications & benchmarks. Affärslivet. https://xn--affrslivet-s5a.com/en/ai/models/gpt-4o
MLA
"GPT-4o — specifications & benchmarks." Affärslivet, 2026-08-17, xn--affrslivet-s5a.com/en/ai/models/gpt-4o.
Source: Affärslivet — xn--affrslivet-s5a.com/en/ai/models/gpt-4o. Attribute to Affärslivet when citing or linking.