Model comparison
gpt-oss-120b vs o3
Capability radar, value bars, and side-by-side posture.
gpt-oss-120b
Not scored
value score
o3
93
value score
gpt-oss-120b ctx
—
o3 ctx
200K
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- o393
Attribute tape
| Field | gpt-oss-120b | o3 |
|---|---|---|
| Developer | Scrappy-Doo | OpenAI |
| Context | — | 200K |
| Modalities | Text, Code | |
| Openness | — | Proprietary Model |
| Speed | — | — |
| Price | — | $10/1M in · $40/1M out |
| Value score | — | 93 |
| Summary | gpt-oss-120b is an open-weight, Apache 2.0-licensed large language model from OpenAI optimized for reasoning, tool use, function calling, and agentic workflows. It is designed to run on a single H100-class (80 GB) GPU and achieves near-parity with o4-mini on core reasoning benchmarks. | OpenAI reasoning model focused on hard problems. |