TPSTokens Per Second

gpt-oss-120b

OpenAI🇺🇸 United States
active

OpenAI's first open-weights model since GPT-2. 117B-param MoE (5.1B active) under Apache 2.0, near o4-mini performance, runs on a single 80GB GPU. Configurable reasoning effort.

Compare with other models →
Context window131K tokens

Version History

gpt-oss-120b-launchmajor

gpt-oss-120b launches. OpenAI's first open-weights model since GPT-2. 117B-param MoE (5.1B active) under Apache 2.0, near o4-mini performance, runs on a single 80GB GPU. Configurable reasoning effort.

Benchmark Scores

Full leaderboard →
1353.0 elo
Arena Elo
78.2%
GPQA
78.1%
Hallucination (Knowledge)
14.2%
Hallucination Rate
87.8%
LiveCodeBench
90.0%
MMLU
80.8%
MMLU-Pro
300.0 tokens_per_sec
Speed (tok/s)