OpenAI

GPT-OSS-120B

by OpenAI

+
+
+
+
About

GPT-OSS-120B, released by OpenAI in August 2025, is an open-weight large language model with 120 billion parameters distributed under the Apache 2.0 license. It represents OpenAI's entry into the open-source model space, enabling developers to self-host and fine-tune a GPT-5-generation-class model. GPT-OSS-120B targets research applications, on-premises deployments, and custom fine-tuning workflows requiring a large open-weight base model.

+
+
+
+
Pricing Range
Input (per 1M)$0.00 -$0.00
Output (per 1M)$0.00 -$0.00
Providers1
+
+
+
+
Timeline
ReleasedAug 1, 2025
+
+
+
+
License & Family
License
Apache 2.0
Performance Overview
Performance metrics and category breakdown

Overall Performance

2 benchmarks
Average Score
39.9%
Best Score
78.3%
High Performers (80%+)
0

Performance Metrics

Max Context Window
132.1K

Top Categories

Science
78.3%
Agents
1.6%
+
+
+
+
All Benchmark Results for GPT-OSS-120B
Complete list of benchmark scores with detailed information
GPQA Diamond
Science
78.30
78.3%
Unverified
BrowseComp
Agents
1.60
1.6%
Unverified