Back to Models

Gpt oss 120b

GPT-OSS-120B is an open-weight MoE model from OpenAI (117B params, 5.1B active). It is optimized for single-GPU deployment and excels in reasoning and agentic tasks.

Thinking Mode
Parameters
117000000000 B
Context
131,072 tokens
Released
Apr 8, 2025

Leaderboards

Performance vs. Industry Average

Intelligence

Gpt oss 120b is of higher intelligence compared to average (4.1), with an intelligence score of 4.2.

Price

Gpt oss 120b is cheaper compared to average ($4.58 per 1M Tokens) with a price of $0.11 per 1M Tokens.

Latency

Gpt oss 120b has a lower average latency compared to average (116.45s), with an average latency of 75.48s.

P99 Latency

Gpt oss 120b has a lower P99 latency compared to average (339.37s), taking 291.84s to receive the first token at P99 (TTFT).

Context Window

Gpt oss 120b has a smaller context window than average (351k tokens), with a context window of 131k tokens.

Gpt oss 120b - AutoBench