Introducing OpenAI o3 and o4-mini

Introducing OpenAI o3 and o4-mini | OpenAI

April 16, 2025

Introducing OpenAI o3 and o4-mini

Loading…

Share

Update on June 10, 2025: OpenAI o3‑pro is now available to Pro users in ChatGPT, as well as in our API. Like OpenAI o1‑pro, o3‑pro is a version of our most intelligent model, OpenAI o3, designed to think longer and provide the most reliable responses. Full details can be found in our release notes⁠.

---

Today, we’re releasing OpenAI o3 and o4-mini, the latest in our o-series of models trained to think for longer before responding. These are the smartest models we’ve released to date, representing a step change in ChatGPT's capabilities for everyone from curious users to advanced researchers. For the first time, our reasoning models can agentically use and combine every tool within ChatGPT—this includes searching the web, analyzing uploaded files and other data with Python, reasoning deeply about visual inputs, and even generating images. Critically, these models are trained to reason about when and how to use tools to produce detailed and thoughtful answers in the right output formats, typically in under a minute, to solve more complex problems. This allows them to tackle multi-faceted questions more effectively, a step toward a more agentic ChatGPT that can independently execute tasks on your behalf. The combined power of state-of-the-art reasoning with full tool access translates into significantly stronger performance across academic benchmarks and real-world tasks, setting a new standard in both intelligence and usefulness.

What’s changed

OpenAI o3 is our most powerful reasoning model that pushes the frontier across coding, math, science, visual perception, and more. It sets a new SOTA on benchmarks including Codeforces, SWE-bench (without building a custom model-specific scaffold), and MMMU. It’s ideal for complex queries requiring multi-faceted analysis and whose answers may not be immediately obvious. It performs especially strongly at visual tasks like analyzing images, charts, and graphics. In evaluations by external experts, o3 makes 20 percent fewer major errors than OpenAI o1 on difficult, real-world tasks—especially excelling in areas like programming, business/consulting, and creative ideation. Early testers highlighted its analytical rigor as a thought partner and emphasized its ability to generate and critically evaluate novel hypotheses—particularly within biology, math, and engineering contexts.

OpenAI o4-mini is a smaller model optimized for fast, cost-efficient reasoning—it achieves remarkable performance for its size and cost, particularly in math, coding, and visual tasks. It is the best-performing benchmarked model on AIME 2024 and 2025. Although access to a computer meaningfully reduces the difficulty of the AIME exam, we also found it notable that o4-mini achieves 99.5% pass@1 (100% consensus@8) on AIME 2025 when given access to a Python interpreter. While these results should not be compared to the performance of models without tool access, they are one example of how effectively o4-mini leverages available tools; o3 shows similar improvements on AIME 2025 from tool use (98.4% pass@1, 100% consensus@8).

In expert evaluations, o4-mini also outperforms its predecessor, o3‑mini, on non-STEM tasks as well as domains like data science. Thanks to its efficiency, o4-mini supports significantly higher usage limits than o3, making it a strong high-volume, high-throughput option for questions that benefit from reasoning. External expert evaluators rated both models as demonstrating improved instruction following and more useful, verifiable responses than their predecessors, thanks to improved intelligence and the inclusion of web sources. Compared to previous iterations of our reasoning models, these two models should also feel more natural and conversational, especially as they reference memory and past conversations to make responses more personalized and relevant.

Multimodal

Coding

All SWE-bench evaluation runs use a fixed subset of n=477 verified tasks which have been validated on our internal infrastructure.

Instruction following and agentic tool use

All models are evaluated at high ‘reasoning effort’ settings—similar to variants like ‘o4-mini-high’ in ChatGPT.

Continuing to scale reinforcement learning

Throughout the development of OpenAI o3, we’ve observed that large-scale reinforcement learning exhibits the same “more compute = better performance” trend observed in GPT‑series pretraining. By retracing the scaling path—this time in RL—we’ve pushed an additional order of magnitude in both training compute and inference-time reasoning, yet still see clear performance gains, validating that the models’ performance continues to improve the more they’re allowed to think. At equal latency and cost with OpenAI o1, o3 delivers higher performance in ChatGPT—and we've validated that if we let it think longer, its performance keeps climbing.

We also trained both models to use tools through reinforcement learning—teaching them not just how to use tools, but to reason about when to use them. Their ability to deploy tools based on desired outcomes makes them more capable in open-ended situations—particularly those involving visual reasoning and multi-step workflows. This improvement is reflected both in academic benchmarks and real-world tasks, as reported by early testers.

Thinking with images

For the first time, these models can integrate images directly into their chain of thought. They don’t just see an image—they think with it. This unlocks a new class of problem-solving that blends visual and textual reasoning, reflected in their state-of-the-art performance across multimodal benchmarks.

People can upload a photo of a whiteboard, a textbook diagram, or a hand-drawn sketch, and the model can interpret it—even if the image is blurry, reversed, or low quality. With tool use, the models can manipulate images on the fly—rotating, zooming, or transforming them as part of their reasoning process.

These models deliver best-in-class accuracy on visual perception tasks, enabling it to solve questions that were previously out of reach. Check out the visual reasoning research blog⁠ to learn more.

Toward agentic tool use

OpenAI o3 and o4-mini have full access to tools within ChatGPT, as well as your own custom tools via function calling in the API. These models are trained to reason about how to solve problems, choosing…