OpenAI: o3 Deep Research
OpenAI's o3 Deep Research is a specialised research-focused model with exceptional GPQA and MMLU Pro scores, making it well-suited for deep analytical and content tasks, though its intelligence index places it in the 'good' tier rather than world-class. At $10/$40 per million tokens it's a premium option best justified for complex research workflows rather than everyday business use.
Assessment date: March 12, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.
Capabilities
Architecture
| Modality | Text + Image + File → Text |
| Tokenizer | GPT |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $10.00 | $0.010000 |
| Output | $40.00 | $0.040000 |
