GPT-5.4 nano vs GPT-5.4-Pro
OpenAI GPT-5.4 nano | OpenAI GPT-5.4-Pro | |
|---|---|---|
| Overview | ||
| Company | OpenAI | OpenAI |
| Release date | Mar 17 2026 | Mar 5 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. | 14% | — |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | — | 89.3% |
Multidisciplinary reasoning Humanity's Last Exam · with toolsHumanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 58.7% |
Abstract reasoning ARC-AGI-2Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | — | 83.3% |
Advanced math FrontierMath · Tier 1–3Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | — | 50% |
Advanced math FrontierMath · Tier 4Very hard, research-level math problems. Tier 4 is the hardest — close to what professional research mathematicians tackle. Higher is better. | — | 38% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 94.4% |
Knowledge work GDPval (win/tie rate)How often the AI's work matches or beats a human expert's on real knowledge-work tasks. Higher is better. | — | 82% |
| Timeline | ||
| Release gap | GPT-5.4-Pro shipped 12 days before GPT-5.4 nano | |
Which is better: GPT-5.4 nano or GPT-5.4-Pro?
GPT-5.4 nano and GPT-5.4-Pro don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GPT-5.4-Pro shipped 12 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.
Direct benchmark comparisons are unavailable — GPT-5.4 nano and GPT-5.4-Pro don't publish scores on any of the same benchmarks.
Frequently asked questions
GPT-5.4 nano was released by OpenAI on Mar 17 2026.
GPT-5.4-Pro was released by OpenAI on Mar 5 2026.
Other comparisons
GPT-5.4 nano vs Claude Sonnet 5GPT-5.4-Pro vs Claude Sonnet 5GPT-5.4 nano vs Gemini 3.5 FlashGPT-5.4-Pro vs Gemini 3.5 FlashGPT-5.4 nano vs Muse Spark 1.1GPT-5.4-Pro vs Muse Spark 1.1GPT-5.4 nano vs Grok 4.5GPT-5.4-Pro vs Grok 4.5GPT-5.4 nano vs DeepSeek-V4-ProGPT-5.4-Pro vs DeepSeek-V4-ProGPT-5.4 nano vs Mistral Medium 3.5GPT-5.4-Pro vs Mistral Medium 3.5