gpt-oss-120b (batch)
by OpenAI
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. I
Models
gpt-oss-120b (batch)
Added 3 Sept 2026
Overview
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...
How to use / API access
Call via OpenRouter with model id `openai/gpt-oss-120b:batch`.
- openrouter ·
openai/gpt-oss-120b:batchDocs
OpenRouter id: openai/gpt-oss-120b:batch
Benchmarks
- Intelligence Index (artificial-analysis) : 15.6 index
- Coding Index (artificial-analysis) : 30.4 index
- Agentic Index (artificial-analysis) : 6.3 index
- Design Arena 3d (other) : 938 elo · #107
- Design Arena codecategories (other) : 980 elo · #113
- Design Arena dataviz (other) : 1006 elo · #104
- Design Arena gamedev (other) : 1021 elo · #104
Notes
gpt-oss-120b (batch) is listed in the EDNA Models directory from the OpenRouter catalogue.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.