gpt-oss-120b
Intelligence benchmarks
Artificial Analysis indexes - compared with the best open and proprietary models
Intelligence
11.6
AA Index
Coding
30.4
AA Index
Agentic
3.7
AA Index
Intelligence Index - gpt-oss-120b vs. the field
Best open-weight models (you can run locally) and leading proprietary models for context.
Coding Index comparison
Agentic Index comparison
Benchmark data from Artificial Analysis · updated 2026-10-19.
Hosted API cost & speed
What it costs to rent this model instead of running it locally
| Metric | Value |
|---|---|
| Input (per 1M tokens) | $0.13 |
| Output (per 1M tokens) | $0.60 |
| Median speed (hosted API) | 258 tok/s |
Median across hosted providers, measured by Artificial Analysis - updated 2026-10-19. Local llama.cpp speed depends on your hardware — see the hardware pages for estimates.
Arena rating (LMArena)
Human preference wins from head-to-head chat battles
| Metric | Value |
|---|---|
| Overall arena rating | 1365.5 |
| Rank (overall) | #192 |
| Battle votes | 30,206 |
Overall rating published by LMArena on 2026-10-15 - a pairwise human-preference Elo across live chat battles; higher is better. Fetched 2026-10-19. Open-weights models compete head-to-head with proprietary ones here — no benchmark prompts, just what people pick.
Standard benchmarks
Performance across standard evaluations
| Benchmark | Score |
|---|---|
| MMLU-Pro | 80.8 |
| GPQA Diamond | 78.2 |
| AIME | 93.4 |
| SWEBENCH | 47.9 |
| HLE | 19.6 |
| SciCode | 34 |
| LiveCodeBench | 87.8 |
| IFBench | 69 |
| Terminal-Bench | 23.5 |
Source: Artificial Analysis component evals - updated 2026-10-19. Additional scores from Hugging Face OpenEvals official leaderboards - updated 2026-10-19.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve openai/gpt-oss-120bNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
gpt-oss-120b
gpt-oss-120b is a 120.4B-parameter apache-2.0 model from openai. It scores 11.6 on the Artificial Analysis Intelligence Index (coding 15.5). At Q4_K_M it needs roughly 70 GB of VRAM, placing it in the 48 GB+ / multi-GPU hardware tier.
Specifications
| Spec | Value |
|---|---|
| Parameters | 120.4B |
| Context length | 131K tokens |
| License | apache-2.0 |
| Modalities | text |
| Released | 2025-08-04 |
| Weights | openai/gpt-oss-120b |
Benchmarks
Artificial Analysis Intelligence Index - gpt-oss-120b vs. leading closed models:
| Model | Intelligence | Coding | GPQA |
|---|---|---|---|
| gpt-oss-120b | 24.5 | 15.5 | 67.2 |
| GPT-5.5 (xhigh) | 60.2 | 59.1 | 93.5 |
| Claude Opus 4.8 (max) | 61.4 | 56.7 | 92 |
| Gemini 3.1 Pro Preview | 57.2 | 55.5 | 94.1 |
| Grok 4.3 (high) | 53.2 | 41 | 90.1 |
Source: Artificial Analysis (2026-06-04).
VRAM requirements
| Quant | VRAM | Runs on |
|---|---|---|
| Q4_K_M | ~70 GB | A100 80GB, H100 |
| Q5_K_M | ~85 GB | multi-GPU / datacenter |
| Q8_0 | ~129 GB | multi-GPU / datacenter |
| FP16 | ~241 GB | multi-GPU / datacenter |
VRAM is estimated from parameter count; MoE models still need all weights resident.
How to run
vLLM:
vllm serve openai/gpt-oss-120bPopularity
gpt-oss-120b has 4,549,787 downloads in the last month on HuggingFace and 4,847 likes.
Frequently asked
Quick answers to common questions
How much VRAM does gpt-oss-120b need?
gpt-oss-120b with 120.4B parameters needs approximately 70 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is gpt-oss-120b better than other openai models?
gpt-oss-120b has 120.4B parameters with 131,072 context - a strong choice for general use.
What license is gpt-oss-120b under?
gpt-oss-120b is released under the apache-2.0 license, making it suitable for most commercial and personal projects.
What hardware runs gpt-oss-120b well?
With 120.4B parameters, gpt-oss-120b requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for gpt-oss-120b?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~85 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can gpt-oss-120b's context window handle?
gpt-oss-120b supports a 131,072-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with gpt-oss-120b?
gpt-oss-120b competes with other 60B–181B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec