Model

gpt-oss-120b (Low)

OPEN

OpenAI · gpt-oss family · released Aug 5, 2025

OpenAI's first open-weight model since GPT-2; 117B MoE (5.1B active), Apache 2.0.

ReasoningCodingVisionFunction callingTool useAgentic

1330.6

Elo · rank #151

Parameters

117B

Active params

5.1B (MoE)

Context

128K tokens

Architecture

Mixture-of-experts transformer, 128 experts/layer, top-4 active, 36 layers

License

Apache 2.0

Languages

—

API price (in/out)

No hosted API

Modalities

text

Benchmark results

Bar shows position within the tracked field; marker = field best

Aider PolyglotCoding24.0%#35

best: Claude Opus 4.5 · 89.4%

AIMEMath56.3%#114

best: GPT-5.2 · 100.0%

CodeforcesCoding1595#35

best: DeepSeek-V4-Pro (Think Max) · 3206

GDPval-AAAgents397#40

best: Claude Fable 5 · 1932

GPQA DiamondReasoning67.1%#133

best: GPT-5.6 · 94.6%

Humanity's Last ExamReasoning5.2%#115

best: Claude Sonnet 5 · 57.4%

IFBenchReasoning58.0%#31

best: MiniMax M3 · 83.0%

MMLUKnowledge85.9%#50

best: OpenAI o3 · 92.9%

MMMLUKnowledge74.1%#36

best: Gemini 3.1 Pro · 92.6%

SWE-bench VerifiedCoding47.9%#94

best: Claude Fable 5 · 95.0%

tau-benchAgents49.4%#22

best: Claude Opus 4.1 · 82.4%

Terminal-Bench 2.0Coding14.0%#59

best: GPT-5.6 · 88.8%

Run it locally

VRAM @ Q4

73 GB

VRAM @ FP16

234 GB

Fits on (Q4)

M3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB

Does not fit on a single RTX 4090 (24GB); OpenAI specifies a single 80GB GPU (H100/MI300X) for native MXFP4 inference.

Quantizations

MXFP4 (native) · GGUF Q4_K_M · GGUF Q8_0

gpt-oss family

Elo progression across releases

gpt-oss-120b (High)Aug 20251845.2 gpt-oss-120b (Low)Aug 20251330.6 gpt-oss-120b (Medium)Aug 20251555.0 gpt-oss-20b (High)Aug 20251540.0 gpt-oss-20b (Low)Aug 20251071.0 gpt-oss-20b (Medium)Aug 20251367.6

Resources

HFopenai/gpt-oss-120b GHopenai/gpt-oss DOCScookbook.openai.com APIAvailable via OpenAI API

API price weights · each benchmark row carries its own source badge (see methodology)