OpenAI o3
OpenAI's April 2025 reasoning model for math, science and coding, deprecated in the API since June 2026 with shutdown set for December 2026.
Our editorial assessment, based on the public sources listed below. Last reviewed .
- Overall rank
- #65
- Tier
- A
- Score
- 72.8
- Main category
- Reasoning
Strengths
- Strong on complex multi-step problems
- Full tool access support
- Analytical rigor praised by early testers
Considerations
- Deprecated; OpenAI recommends moving to GPT-5.6 Sol before the December 11, 2026 shutdown
- 200K-token context window, smaller than the 1M-class windows of current OpenAI models
Price
API $2 input / $8 output per 1M tokens (deprecated; shutdown December 11, 2026)
Shown for reference — price is not part of the score.
Score breakdown
- Performance
- 76.0
- 55% of score
- Reputation
- 80.0
- 35% of score
- Recency
- 30.0
- 10% of score
The overall score combines these sub-scores using the weights shown. How we score →
Verification status
Each field carries its own re-verification date. Amber means older than 90 days — treat those figures as stale until re-checked.
- Pricing
- Benchmark
- Reputation
- Feature list
Checked against the sources listed below.
Sources
- Introducing OpenAI o3 and o4-mini (opens in a new tab)Accessed:
- Model Release Notes | OpenAI Help Center (opens in a new tab)Accessed:
- Introducing Claude 4 (opens in a new tab)Accessed:
- TeamAI — 2026 AI Frontier Model War (opens in a new tab)Accessed:
- Frontier AI Models 2026: GPT-5.3, Claude 4.6, G - TeamDay.ai (opens in a new tab)Accessed:
Show 5 more sources
Similar models
- Nemotron 3 SuperNVIDIA#37 · Tier A · Score 81.8Compare
- Gemini 3.1 ProGoogle#48 · Tier A · Score 79.0Compare
- Gemini 2.5 ProGoogle#61 · Tier A · Score 74.3Compare
- gpt-oss-120bOpenAI#70 · Tier A · Score 70.5Compare