o3
OpenAIProprietaryReasoningVerifiedReleased Apr 16, 2025Input: image, text, file
Overall score
45.4
Rank 122 of 222 · 39.2–51.6
Context window
200K
200,000 tokens
Price per 1M tokens
$2.00 in · $8.00 out
✓ Verified on OpenAI's pricing page
Blended price
$3.50
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Instruction following#3887.4
- 2Reasoning76.3
- 3Multimodal67.8
- 4Knowledge62.6
- 5Math48.5
Benchmark results (2)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Multimodal
| Design Arena Website | 1036 | #84 of 91 |
Math
| FrontierMath v2 (Tiers 1-3) | 33.333 | #52 of 64 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| ✓ Official (OpenAI) checked Oct 17, 2026 · o3 | $2.00 | $8.00 | $0.50 |
| BenchLM list price | $2.00 | $8.00 | $0.50 |
| OpenRouter openai/o3 | $2.00 | $8.00 | $0.50 |
Standard tier, prompts under 272K tokens.
OpenAI's o3 model page lists $2.00 input / $8.00 output per million tokens.
Arena ratings
Human-preference ratings from LMArena. Best-rated variant shown.
| Vision(2025-04-16) | 1214 | #86 · 45.6K votes |
Speed
Measured by us through OpenRouter (median of trials).
Not measured yet.
Related models
Same family
Similar score
- o3-pro45.4 · $35.00
- Nemotron 3.5 Bolt 74B-A9B45.3 · —
- Gemma 4 26B A4B45.6 · $0.12
- Ling 3.0 Flash45.1 · $0.032
- Qwen3.5-35B-A3B45.8 · $0.35