OpenAI
GPT-4o (2024-08-06)
The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities. For benchmarking against other models, it was briefly called ["im-also-a-good-gpt2-chatbot"](https://twitter.com/LiamFedus/status/1790064963966370209)
- Input / 1M tokens
- $2.50
- Output / 1M tokens
- $10.00
- Context window
- 128K tokens
- Provider
- OpenAI
- Cached input / 1M
- $1.25
- Knowledge cutoff
- 2023-10-31
Performance
Median streaming throughput and first-token latency measured by Artificial Analysis.
- Output tokens / sec
- 108 t/s
- Time to first token
- 0.60s
Benchmarks
Intelligence, coding, and math indexes plus the underlying evaluation scores.
- Intelligence Index
- 19
- Coding Index
- 17
- Math Index
- —
- MMLU-Pro
- —
- GPQA
- 52.1%
- HLE
- 2.9%
- LiveCodeBench
- 31.7%
- SciCode
- 33.1%
- MATH-500
- 79.5%
- AIME
- 11.7%
Benchmarks via Artificial Analysis