OpenAI: gpt-oss-120b (batch)
8.8 / 10
131.1K context
Proprietary
About this model
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
Benchmark Scores
MMLU
90.0
IFEval
69.0
AIME-2024
96.6
AIME-2025
97.9
Technical Specs
- Architecture: text->text
- Context Window: 131,072 tokens
- Input Modalities: text
Hardware Requirements
- API-only (no local hardware needed)
Pricing
| Input | Output | Currency |
|---|---|---|
| 0.15 / 1M tokens | 0.6 / 1M tokens | USD |