GPT-5.1 vs GPT-5.4 nano
OpenAI GPT-5.1 | OpenAI GPT-5.4 nano | |
|---|---|---|
| Overview | ||
| Company | OpenAI | OpenAI |
| Release date | Nov 12 2025 | Mar 17 2026 |
| Access | Proprietary | Proprietary |
| 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 | 14% |
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-5.1 shipped 125 days before GPT-5.4 nano | |
Which is better: GPT-5.1 or GPT-5.4 nano?
GPT-5.1 leads GPT-5.4 nano on 1 of the 1 benchmark they both report (BullshitBench v2). GPT-5.1 shipped 125 days before GPT-5.4 nano, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On BullshitBench v2, GPT-5.1 leads at 25% vs GPT-5.4 nano at 14%.
Frequently asked questions
GPT-5.1 was released by OpenAI on Nov 12 2025.
GPT-5.4 nano was released by OpenAI on Mar 17 2026.
Other comparisons
GPT-5.1 vs Claude Sonnet 5GPT-5.4 nano vs Claude Sonnet 5GPT-5.1 vs Gemini 3.5 FlashGPT-5.4 nano vs Gemini 3.5 FlashGPT-5.1 vs Muse Spark 1.1GPT-5.4 nano vs Muse Spark 1.1GPT-5.1 vs Grok 4.5GPT-5.4 nano vs Grok 4.5GPT-5.1 vs DeepSeek-V4-ProGPT-5.4 nano vs DeepSeek-V4-ProGPT-5.1 vs Mistral Medium 3.5GPT-5.4 nano vs Mistral Medium 3.5