Ctrl K
Back to models

OpenAI

gpt-oss-120b

  • Released
  • Open weights
  • Apache 2.0
Compare
Intelligence Index

High setting

11.6#66 of 83measured models
Measured · Artificial Analysis v4.3.2
API price from
$0.03 in / ≈ $0.19 out / 1M tokOpenRouter · AkashML · BF16
Context window
131.07K tok

Performance profile

ReasoningRank #56 of 107
78.2%
GPQA Diamond
CodingRank #77 of 94
34.0%
SciCode
Cost efficiencyRank #24 of 67
125.9pts / $
Intelligence ÷ eval cost

Capabilities

Context window

Modalities

Measured settings

Avg reasoning tokens / task — Artificial Analysis Intelligence Index v4.3.2: weighted average reasoning tokens per benchmark task, not a token limit. Source (opens in a new tab)

Integration

Reasoning trade-offs

Source (opens in a new tab)
Intelligence Index v4.3.2
gpt-oss-120b
Cost per task (USD) · log scale
gpt-oss-120bHigh
Intelligence Index
11.6
Cost / task
$0.0922
Evaluation time
1.9m

Pricing & access

API route
OpenRouter · AkashML · BF16API
Tier & contextStandard

USD per 1M tokens

Input
$0.03
Output
$0.187
Cached input
$0.03

Run locally

GGUFMXFP4
Context
Estimated memory

~65.5 GiB

RAM + VRAM

Estimate assumptions

One text chat at the selected context, with a 16-bit cache and app allowance. Operating system and image processing are extra; optimized caches can use less.

96 GiB RAMwithout GPU offload

Memory budgetOne text chat
Weights
59 GiB
Context cache
0.6 GiB16-bit cache
App allowance
5.9 GiB
Download
63.4 GB2 files · keep together
Disk space
~75 GB
Available software
Ollama (opens in a new tab)LM Studio (opens in a new tab)Jan (opens in a new tab)KoboldCpp (opens in a new tab)llama.cpp (opens in a new tab)
Get GGUF (opens in a new tab)
Set up in Ollama · MXFP4 · 8K context

Save the following as Modelfile. The context matches the estimate above.

FROM hf.co/lmstudio-community/gpt-oss-120b-GGUF:MXFP4
PARAMETER num_ctx 8192

Then run these commands in your terminal:

ollama create llmcurrent-local -f Modelfile
ollama run llmcurrent-local

Ollama import instructions (opens in a new tab) · For LM Studio or Jan, open the app’s model search, enter lmstudio-community/gpt-oss-120b-GGUF, choose MXFP4, and set context to 8,192 tokens in the app’s model settings. Software links above open each app’s setup guide.

vLLM setup (opens in a new tab)

Benchmarks

Full leaderboardSource (opens in a new tab)

Humanity’s Last Exam

Frontier reasoning

gpt-oss-120b · High#66 of 126

  1. 1Claude Opus 5.5Max61.4%
  2. 2Claude Fable 5.1Max59.1%
  3. 3Gemini 4 ArgonHigh57.1%
  5. 63Ring-2.6-1TExtra high21.6%
  6. 64o3Reasoning20.1%
  7. 65GPT-5.5 Instant (June 2026)Reasoning19.9%
  8. 66gpt-oss-120bHigh19.6%
  9. 67Gemma 4 26B A4BReasoning19.3%
  10. 68Gemini 3.5 Flash-LiteHigh18.8%
  11. 69Quasar 438BMax18.7%

Peers use their best measured result on this benchmark.

Alternatives

Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.