RSS

OpenAI

o3

Benchmarks, price, context and versions

Direct answer: o3 is a model from OpenAI. 81.8% on GPQA Diamond, per Epoch AI. On OpenRouter, US$ 2.00 per 1 million input tokens and US$ 8.00 per 1 million output tokens.

✓ Good for

  • Not enough data in the open sources this section uses to build this block.

✕ Not the best for

  • the ceiling of reasoning on research-level math (#65 of 86 on FrontierMath (tiers 1 to 3))
  • fixing bugs in real code (#27 of 32 on SWE-bench Verified)
  • when the input budget sits at the top of the table (input price in the highest 25% on OpenRouter)

This block follows a rule of this section, using source data: if the model is in the top 25% of the metric, the item goes under "Good for"; if it is in the bottom half, it goes under "Not the best for". The middle band appears in neither. Price and context use OpenRouter; scores use Epoch AI or OpenRouter Benchmarks, in the latest version we checked.

Benchmarks

GPQA Diamond

?what it is
81.8%

highest score on this metric 96.4%

87º / 198 · Epoch AI, latest version we checked

OTIS Mock AIME

?
84.4%

highest score on this metric 100%

81º / 186 · Epoch AI, latest version we checked

FrontierMath (tiers 1 to 3)

?
33.3%

highest score on this metric 95.1%

65º / 86 · Epoch AI, latest version we checked

SimpleQA Verified

?
49.4%

highest score on this metric 94%

31º / 87 · Epoch AI, latest version we checked

SWE-bench Verified

?
62.3%

highest score on this metric 83.5%

27º / 32 · Epoch AI, latest version we checked

Key specs

Origin
the US
Family
o3 provisional data
Weights?
closed
License
no data
Input US$/1M?
US$ 2.00
Output US$/1M
US$ 8.00
Context?
200,000 tokens
Parameters
no data
Input
file, image, text
OpenRouter usage?
no data
Downloads (30 days)?
no data
Use cases provisional data
Text Agents Code
Dates in sources
  • 2025, published, per Epoch AI
  • 2025, listed on OpenRouter

Version history

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch.

FAQ

What is o3?

o3 is a model from OpenAI, with closed weights, used for text, agents, code.

How much does o3 cost?

On OpenRouter, US$ 2.00 per 1 million input tokens and US$ 8.00 per 1 million output tokens.

What is the context window of o3?

200,000 tokens, per OpenRouter.

Is o3 open source?

No. It is available through API only.

What is o3's GPQA Diamond score?

81.8% on GPQA Diamond, per Epoch AI.

Is o3 good for coding?

It scores 62.3% on SWE-bench Verified, per Epoch AI.

Who made o3?

It was made by OpenAI, a lab from the US.

provisional data Questions under review: Semrush had no API balance during collection. Answers use source data only.

Models from OpenAI

See lab

Sources

  • Epoch AI, CC BY 4.0, latest version we checked.
  • OpenRouter, dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.