Model comparison
o3 vs GPT-4.1
Capability radar, value bars, and side-by-side posture.
o3
93
value score
GPT-4.1
90
value score
o3 ctx
200K
GPT-4.1 ctx
1.0M
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- o393
- GPT-4.190
Attribute tape
| Field | o3 | GPT-4.1 |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Context | 200K | 1.0M |
| Modalities | Text, Code | Text, Code, Image |
| Openness | Proprietary Model | Proprietary Model |
| Speed | — | — |
| Price | $10/1M in · $40/1M out | $2/1M in · $8/1M out |
| Value score | 93 | 90 |
| Summary | OpenAI reasoning model focused on hard problems. | Long-context GPT for developer workflows. |