OpenAI

o3

CTX200K

74Quality

Reasoning · Vision · Tools

Input$2/M

Output$8/M

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

PaidProprietary546/1044

Drag to turn

OpenAITextRare

o3

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

o3

Type: Text
Quality: 74 · Top 26% on the Epoch Capabilities Index
Context window: 200,000 tokens
Max output: 100,000 tokens
Input price: $2.00 / 1M tokens
Output price: $8.00 / 1M tokens
Cache read: $0.50 / 1M tokens
Cache write: —
Released: Apr 16, 2025
Knowledge cutoff: May 2024
Takes in: Text, Image, PDF
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
File attachments: Yes
Access: Paid
License: Proprietary
Rarity: Rare
Set number: 546/1044

Open OpenAI docs Quality 74 Evolution 2/2 Meet its creature Battle Kimi K2.7 Code HighSpeed

Weights aren’t public. Use is governed by OpenAI’s terms. Specs from models.dev, last changed Oct 19, 2026. Official source: platform.openai.com.

How good is it?

Public leaderboard scores for o3, refreshed daily from Epoch AI and LMArena.

Top 26% of the 277 models on the Epoch Capabilities Index: #72.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Epoch Capabilities Index#72 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.146.9 index
LMArena Text#140 of 416
People compare two anonymous answers and vote for the better one.1,410 rating
Listed as o3-2025-04-16
LMArena Text · Coding#166 of 411
The text arena’s coding prompts only.1,407 rating
Listed as o3-2025-04-16
LMArena Text · Math#108 of 400
The text arena’s math prompts only.1,426 rating
Listed as o3-2025-04-16
LMArena Text · Creative writing#156 of 414
The text arena’s creative writing prompts only.1,359 rating
Listed as o3-2025-04-16
LMArena Vision#85 of 165
Questions about images, voted by people.1,214 rating
Listed as o3-2025-04-16

Benchmarks Epoch AI runs

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Face off

Current text models from other labs at a similar output price.

o3

o3

How good is it?

Leaderboards

Benchmarks Epoch AI runs

Face off

More from OpenAI

GPT-6.1 Sol

GPT-6 Sol

GPT-6 Luna

GPT-6 Astra

GPT-5.6 Terra

GPT-5.6 Sol

GPT-5.6 Luna

GPT-5.6