Model
Model explorer

OpenAI o3-pro

CLOSED
OpenAI · o3 family · released Jun 10, 2025

Higher-compute o3 variant for the most reliable answers; replaced o1-pro.

ReasoningCodingVisionFunction callingTool useAgentic
2103.6
Elo · rank #51
Parameters
Undisclosed
Active params
—
Context
200K tokens
Architecture
Dense transformer reasoning model, extended test-time compute (exact size undisclosed)
License
Proprietary (OpenAI API Terms)
Languages
—
API price (in/out)
$20 / $80
Modalities
text · vision
Benchmark results
Bar shows position within the tracked field; marker = field best
Aider PolyglotCoding84.9%#3
best: Claude Opus 4.5 · 89.4%
AIMEMath93.0%#31
best: GPT-5.2 · 100.0%
CodeforcesCoding2748#5
best: DeepSeek-V4-Pro (Think Max) · 3206
GPQA DiamondReasoning84.0%#61
best: GPT-5.6 · 94.6%
SWE-bench VerifiedCoding75.0%#41
best: Claude Fable 5 · 95.0%
Run it locally
Closed weights — available via API only. No local deployment.
Input / M tok
$20
Output / M tok
$80
o3 family
Elo progression across releases
OpenAI o3-mini (High)Jan 20251653.0OpenAI o3-mini (Low)Jan 20251334.3OpenAI o3-mini (Medium)Jan 20251485.5OpenAI o3Apr 20251926.8OpenAI o3-proJun 20252103.6
Resources
DOCSdevelopers.openai.comAPIAvailable via OpenAI API
API price $20/$80 · each benchmark row carries its own source badge (see methodology)