OpenAI
gpt-oss-120b
ReasoningOpen weights
- Intelligence
- 10.2
- Rank 424 of 747 measured models
- Coding
- 21.2
- Rank 220 of 298 measured models
- Output speed
- 232 t/s
- Rank 25 of 406 measured models
- Price/1M
- $0.237
- Rank 184 of 664 measured models
- Context window
- 131K
- Rank 742 of 1207 measured models
gpt-oss-120b (Low) scores 10.2 on the Artificial Analysis Intelligence Index, ranking 424th of 747 measured models. The closest models on this index are Nemotron 3 Nano Omni 30B A3B Reasoning (10.3), GPT-4.1 mini (10.2), and MiniMax M1 40k (10.0). At $0.237 per million tokens (3:1 input/output blended price), it is cheaper than Nemotron 3 Nano Omni 30B A3B Reasoning ($0.45) and GPT-4.1 mini ($0.70). With an output speed of 232 t/s, it is faster than GPT-4.1 mini (148 t/s), about as fast as Nemotron 3 Nano Omni 30B A3B Reasoning (237 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Nemotron 3 Nano Omni 30B A3B Reasoning
NVIDIA · $0.45 · 237 t/s
10.3+0.1$0.45237 t/sCompare - GPT-4.1 mini
OpenAI · $0.70 · 148 t/s
10.2$0.70148 t/sCompare - MiniMax M1 40k
MiniMax · — · —
10.0−0.2——Compare - Nova 2.0 Pro Preview
Amazon · $3.44 · 112 t/s
10.0−0.2$3.44112 t/sCompare
