GPT-5.1 vs gpt-oss-120b
OpenAI GPT-5.1 | OpenAI gpt-oss-120b | |
|---|---|---|
| Overview | ||
| Company | OpenAI | OpenAI |
| Release date | Nov 12 2025 | Aug 5 2025 |
| Access | Proprietary | Open Weight |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 25%Best | 11% |
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 76.3% | — |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 88.1% | — |
Multimodal MMMUTests the AI on understanding images and text together across many college subjects. Higher is better. | 76% | — |
| Timeline | ||
| Release gap | gpt-oss-120b shipped 99 days before GPT-5.1 | |
Which is better: GPT-5.1 or gpt-oss-120b?
GPT-5.1 leads gpt-oss-120b on 1 of the 1 benchmark they both report (BullshitBench v2). gpt-oss-120b shipped 99 days before GPT-5.1, so benchmark comparisons should account for the intervening progress.
GPT-5.1 is proprietary, while gpt-oss-120b is open weight.
On BullshitBench v2, GPT-5.1 leads at 25% vs gpt-oss-120b at 11%.
Frequently asked questions
GPT-5.1 was released by OpenAI on Nov 12 2025.
gpt-oss-120b was released by OpenAI on Aug 5 2025.
GPT-5.1 is a proprietary model released by OpenAI. gpt-oss-120b is an open weight model released by OpenAI.
Other comparisons
GPT-5.1 vs Claude Sonnet 5gpt-oss-120b vs Claude Sonnet 5GPT-5.1 vs Gemini Omnigpt-oss-120b vs Gemini OmniGPT-5.1 vs Muse Spark 1.1gpt-oss-120b vs Muse Spark 1.1GPT-5.1 vs Grok 4.5gpt-oss-120b vs Grok 4.5GPT-5.1 vs DeepSeek-V4-Progpt-oss-120b vs DeepSeek-V4-ProGPT-5.1 vs Mistral Medium 3.5gpt-oss-120b vs Mistral Medium 3.5