Claude 3.5 Sonnet (upgraded) vs GPT-5.4-Pro
Anthropic Claude 3.5 Sonnet (upgraded) | OpenAI GPT-5.4-Pro | |
|---|---|---|
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Oct 22 2024 | Mar 5 2026 |
| Access | Proprietary | Proprietary |
| Benchmarks | ||
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. | 49% | — |
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 | Claude 3.5 Sonnet (upgraded) shipped 499 days before GPT-5.4-Pro | |
Which is better: Claude 3.5 Sonnet (upgraded) or GPT-5.4-Pro?
Claude 3.5 Sonnet (upgraded) and GPT-5.4-Pro don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude 3.5 Sonnet (upgraded) shipped 499 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.
Direct benchmark comparisons are unavailable — Claude 3.5 Sonnet (upgraded) and GPT-5.4-Pro don't publish scores on any of the same benchmarks.
Frequently asked questions
Claude 3.5 Sonnet (upgraded) was released by Anthropic on Oct 22 2024.
GPT-5.4-Pro was released by OpenAI on Mar 5 2026.
Other comparisons
Claude 3.5 Sonnet (upgraded) vs Gemini OmniGPT-5.4-Pro vs Gemini OmniClaude 3.5 Sonnet (upgraded) vs Muse Spark 1.1GPT-5.4-Pro vs Muse Spark 1.1Claude 3.5 Sonnet (upgraded) vs Grok 4.5GPT-5.4-Pro vs Grok 4.5Claude 3.5 Sonnet (upgraded) vs DeepSeek-V4-ProGPT-5.4-Pro vs DeepSeek-V4-ProClaude 3.5 Sonnet (upgraded) vs Mistral Medium 3.5GPT-5.4-Pro vs Mistral Medium 3.5Claude 3.5 Sonnet (upgraded) vs Kimi K2.7 CodeGPT-5.4-Pro vs Kimi K2.7 Code