gpt-oss-120b
OpenAI · 2 thinking configurations
Intelligence11.6
Input / 1M$0.15
Output / 1M$0.60
Context131.1K
Tariff: OpenAI · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost1 measured configurations · 1 without both values
Selected: thinking high · Click a point to switch configuration
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...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
11.6 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
78.2 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
19.6 %SciCodeCode generation for scientific research problems.
34.0 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
26.2 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
65.8 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
69.0 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
21.8 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputYes
Speed219.0 tok/s
First token0.88 s
Maximum output118K
Catalog listing date2025-08-05