Analysis Summary
OpenAI's free gpt-oss-120b listing is a text-only model with a 131K context window and support for tool use and function calling. Its coding index is 30.4, and its live coding benchmark result is a relative strength in the supplied data. In contrast, its intelligence index is 11.6 and its agentic index is 3.7, so coding results should not be taken as evidence of broad reasoning or autonomous workflow reliability.
The free listing makes it worth testing for coding support and narrowly defined tool-connected tasks where cost is a priority. It is less suitable as the sole model for complex research, nuanced client content, or multi-step agents. The provided data also does not list vision or multimodal input.
Consider it for controlled pilots and tasks with clear acceptance checks. Keep human review in the loop, particularly when code or tool actions affect production systems.
Assessed September 23, 2026
Editorial notes
The free gpt-oss-120b listing pairs strong live coding results with tool and function calling at a 131K context window; its reasoning and agentic indices remain limited.
The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?
DFO Verdict
The free gpt-oss-120b listing pairs strong live coding results with tool and function calling at a 131K context window; its reasoning and agentic indices remain limited.
Benchmarks
Artificial Analysis data refreshed Nov 20, 2026. Arena ratings from the Nov 19, 2026 text leaderboard, with style control. Bars: magenta = reasoning, ink = coding and agents, cyan = instructions and long context.
How OpenAI: gpt-oss-120b (free) compares
OpenAI: gpt-oss-120b (free) ranks #376 of 458 AI models we track for overall intelligence, #74 of 199 for coding, #117 of 181 for agentic tasks. Its 131K-token context window is larger than 48% of the models we list. OpenAI: gpt-oss-120b (free) is currently free to use via OpenRouter.
Dark bar = input · light bar = output, scaled to the priciest peer.
1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.
About OpenAI: gpt-oss-120b (free)
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..
Explore Related Models
Frequently asked questions about OpenAI: gpt-oss-120b (free)
How much does OpenAI: gpt-oss-120b (free) cost?
OpenAI: gpt-oss-120b (free) is currently available for free via OpenRouter.
What is the context window of OpenAI: gpt-oss-120b (free)?
OpenAI: gpt-oss-120b (free) has a context window of 131,072 tokens (131K).
Is OpenAI: gpt-oss-120b (free) good for coding?
On our coding benchmark index, OpenAI: gpt-oss-120b (free) ranks #74 of 199 models, placing it in the broader range of the field for code generation and debugging.
What can OpenAI: gpt-oss-120b (free) do?
OpenAI: gpt-oss-120b (free) supports tool use and function calling.
Who created OpenAI: gpt-oss-120b (free)?
OpenAI: gpt-oss-120b (free) is developed by OpenAI and was released on August 5, 2025.
Benchmarks from Artificial Analysis, pricing from the OpenRouter API, and verdicts from our own testing.
Last updated: November 20, 2026 7:38 pm