OpenAI model product
GPT-OSS-20B
9B parameters) achieves near-parity with OpenAI o4-mini on core reasoning benchmarks, while running efficiently on a single 80 GB GPU.
Updated Aug 12, 2026. Default version: GPT OSS 20B High
LLMBoard score46.5GPT OSS 20B High
Coverage40%2 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable
GPT-OSS-20B Specifications
Technical details for the model's default version.
- Version
- GPT OSS 20B High
- Released
- Aug 5, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 20.9B
- Context window
- 131.1K
- Max output
- 131.1K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Apache 2.0
GPT-OSS-20B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-OSS-20B Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
GPT-OSS-20B Runtime Performance
Provider-specific output speed and catalog latency for GPT OSS 20B High. Runtime does not affect the capability score.
| OpenAI | 100 tok/s | 6.5 s | 131.1K | 131.1K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GPT-OSS-20B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GPT-OSS-20B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| GPT OSS 20B | N/A | 20.9B | 131.1K | 32.8K | Yes | Apache 2.0 | |
| GPT OSS 20B High | 46.5 | 20.9B | 131.1K | 131.1K | No | Apache 2.0 |
What is GPT-OSS-20B?
Key information about GPT-OSS-20B and its available data.
9B parameters) achieves near-parity with OpenAI o4-mini on core reasoning benchmarks, while running efficiently on a single 80 GB GPU.
The gpt-oss-20b model delivers similar results to OpenAI o3‑mini on common benchmarks and can run on edge devices with just 16 GB of memory, making it ideal for on-device use cases, local inference, or rapid iteration without costly infrastructure.
Both models also perform strongly on tool use, few-shot function calling, CoT reasoning (as seen in results on the Tau-Bench agentic evaluation suite) and HealthBench (even outperforming proprietary models like OpenAI o1 and GPT‑4o). 9B parameters.
Data as of 2026-08-11.
GPT-OSS-20B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to GPT-OSS-20B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
o4 mini
OpenAI
OP
GPT-5-mini
OpenAI
OP
GPT-5.4-nano
OpenAI
OP
GPT-OSS-120B
OpenAI
OP
GPT-5-Codex
OpenAI
OP
GPT-5.1-Codex
OpenAI
FAQ
Common questions about GPT-OSS-20B.
When was GPT-OSS-20B released?
GPT-OSS-20B's default version was released on Aug 5, 2025.
How much does GPT-OSS-20B cost?
No official standard PAYG price is currently available for GPT-OSS-20B.
Who created GPT-OSS-20B?
GPT-OSS-20B was created by OpenAI.
What is the context window for GPT-OSS-20B?
The default version has a 131.1K token context window.
Is GPT-OSS-20B open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-OSS-20B?
No provider offering is currently linked to the default version.
What models should I compare GPT-OSS-20B with?
Nearby ranked alternatives include Grok 3 Mini, MiMo V2.5 Pro, Grok 4.1.