GPT-5.4-ProvsGrok 4.20 Beta
GPT-5.4-Pro | Grok 4.20 Beta | |
|---|---|---|
| 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. | — | 56% |
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%Best | 53.3% |
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% | — |
Community preference Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better. | — | 1475 |
| Overview | ||
| Company | OpenAI | SpaceXAI |
| Release date | Mar 5 2026 | Feb 17 2026 |
| Access | Proprietary | Proprietary |
Which is better: GPT-5.4-Pro or Grok 4.20 Beta?
GPT-5.4-Pro leads Grok 4.20 Beta on 1 of the 1 benchmark they both report (ARC-AGI-2). Grok 4.20 Beta shipped 16 days before GPT-5.4-Pro, 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 ARC-AGI-2, GPT-5.4-Pro leads at 83.3% vs Grok 4.20 Beta at 53.3%.
Frequently asked questions
GPT-5.4-Pro was released by OpenAI on Mar 5 2026.
Grok 4.20 Beta was released by SpaceXAI on Feb 17 2026.
GPT-5.4-Pro leads on ARC-AGI-2 — GPT-5.4-Pro 83.3% vs Grok 4.20 Beta 53.3%.
Other comparisons
GPT-5.4-ProvsClaude Opus 5Grok 4.20 BetavsClaude Opus 5GPT-5.4-ProvsGemini 3.6 FlashGrok 4.20 BetavsGemini 3.6 FlashGPT-5.4-ProvsMuse Spark 1.1Grok 4.20 BetavsMuse Spark 1.1GPT-5.4-ProvsDeepSeek-V4-Flash-0731Grok 4.20 BetavsDeepSeek-V4-Flash-0731GPT-5.4-ProvsMistral Medium 3.5Grok 4.20 BetavsMistral Medium 3.5GPT-5.4-ProvsKimi K3Grok 4.20 BetavsKimi K3