o3 by OpenAI demonstrates strong general intelligence, solid coding performance, outstanding mathematical reasoning. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
General Benchmarks
Human preference ELO from blind head-to-head votes
LMSYS / HuggingFaceMassive Multitask Language Understanding professional benchmark
HuggingFace LeaderboardCoding Benchmarks
Human preference ELO for building things — websites, UI, games, charts, SVG
Design Arena (via OpenRouter)Human preference ELO for building a working web page from a brief
Design Arena (via OpenRouter)Math Benchmarks
Reasoning Benchmarks
Speed Benchmarks
Cost Benchmarks
Cost per 1M cached input tokens — the price that actually applies to a long agent conversation
OpenRouter APIContext Benchmarks
Available from 18 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 4 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Poe | $1.8 | $7.2 | $0.45 | 200K | — |
| 302.AI | $2 | $8 | — | 200K | — |
| Abacus | $2 | $8 | $0.5 | 200K | — |
| Azure | $2 | $8 | $0.5 | 200K | Supported |
| Azure Cognitive Services | $2 | $8 | $0.5 | 200K | — |
| Cloudflare AI Gateway | $2 | $8 | $0.5 | 200K | — |
| DevPass (LLM Gateway) | $2 | $8 | $0.5 | 200K | — |
| Eden AI | $2 | $8 | $0.5 | 200K | — |
| Impossibl | $2 | $8 | $0.5 | 200K | — |
| Kilo Gateway | $2 | $8 | $0.5 | 200K | — |
| LLM Gateway | $2 | $8 | $0.5 | 200K | — |
| Merge Gateway | $2 | $8 | $0.5 | 200K | — |
| NEAR AI Cloud | $2 | $8 | $0.5 | 200K | — |
| OpenAI | $2 | $8 | $0.5 | 200K | Supported |
| OpenRouter | $2 | $8 | $0.5 | 200K | Supported |
| Vercel AI Gateway | $2 | $8 | $0.5 | 200K | Supported |
| Jiekou.AI | $10 | $40 | — | 131K | — |
| AnyAPI | — | — | — | 200K | — |
o3 — Benchmark Scores Overview
Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).
Compare o3 With
o3 — Frequently Asked Questions
How intelligent is o3?
o3 scores 1380 on the Chatbot Arena ELO rating, making it a high-performing AI model. This score is based on blind head-to-head human preference voting.
How much does o3 cost?
o3 costs $2.0 per 1M input tokens and $8.0 per 1M output tokens. This is mid-range pricing for its capability level.
How fast is o3?
o3 generates output at 40 tokens per second, which is slower, prioritizing quality over speed compared to other models. The time to first token is 800 ms.
How good is o3 at coding?
o3 achieves 69.1% on SWE-bench Verified, demonstrating strong real-world software engineering capability. This benchmark tests the model's ability to resolve actual GitHub issues.
How good is o3 at math and reasoning?
o3 scores 96.0% on the MATH benchmark (competition-level mathematics). It also achieves 83.3% on GPQA Diamond, a graduate-level science reasoning benchmark.
What is the context window of o3?
o3 has a context window of 200K tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created o3?
o3 was created by OpenAI. It is classified as a flagship model in our catalogue.
Is o3 open source?
No, o3 is a proprietary model. It is available through OpenAI's API and compatible providers.