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...
Tested on 48 benchmarks · BenchGecko score 46.7. Top scores: Chatbot Arena Elo — Overall (1351.6%), OpenCompass — AIME2025 (93.4%), OpenCompass — IFEval (90.2%).
OpenCompass Live Code Bench v6. Fresh competitive programming problems to evaluate code generation without memorization.
Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.
Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.
Stanford HELM WildBench evaluation. Tests reasoning on challenging real-world tasks.
Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.
Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.
OpenCompass evaluation on AIME 2025 problems. Tests mathematical reasoning on fresh competition problems.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.
- Typetext
- Context131K tokens (~66 books)
- ReleasedAug 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.000
Frequently Asked Questions
Related Models
Qwen3.6 Flash · Alibaba QwenGLM 5V Turbo · z-aio1 · OpenAIGemini 3.1 Flash Lite · Google DeepMindR1 Distill Llama 70B · DeepSeekKey facts · as of 2026-10-05
- gpt-oss-120b by OpenAI. BenchGecko score 46.7, rank 164 of 312 scored models (normalized average of public benchmark scores).
- List price $0.0370 input · $0.17 output per 1M tokens (as of 2026-10-05).
- Sold by 22 providers (as of 2026-10-05): CoreWeave (fp4) $0.0300 in / $0.17 out · DekaLLM (bf16) $0.0300 in / $0.18 out · AkashML (bf16) $0.0370 in / $0.19 out · DeepInfra (bf16) $0.0370 in / $0.17 out · Mancer 2 (fp8) $0.0450 in / $0.25 out · and 17 more. Every provider
How to cite · data as of 2026-10-05
gpt-oss-120b · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/gpt-oss-120b
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP