gpt-oss-120b (High)
Descripción
GPT-OSS-120B is an open-weight, 116.8B-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 to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation. It achieves near-parity with OpenAI o4-mini on core reasoning benchmarks. Note: While referred to as '120b' for simplicity, it technically has 116.8B parameters.
Radar de capacidades
Science se estima a partir de las puntuaciones científicas de LLM Stats o del razonamiento cuando no hay benchmarks científicos dedicados.
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Capacidad agéntica | 102 | 42.0 | LS |
| Ranking general | 69 | 3.0 | AA |
| Ciencia | 69 | 8.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Agents
Chat
General
Healthcare
Instruction Following
Language
Math
Reasoning
Índices de evaluación AA
(Artificial Analysis)Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Precios
Velocidad
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
63 proveedores
Comparar precios entre diferentes proveedores de API para este modelo.