GPT-5.4-ProvsQwen3.6
GPT-5.4-Pro | Qwen3.6 | |
|---|---|---|
| Specifications | ||
Parameters | — | 35B |
Context window | — | 256k |
| Benchmarks | ||
Agentic coding SWE-Bench ProCan the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | — | 49.5% |
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. | — | 73.4% |
Multilingual coding SWE-Bench MultilingualLike SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 67.2% |
Agentic terminal coding Terminal-Bench 2.0Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 51.5% |
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 · no toolsHumanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 21.4% |
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%Best | 86% |
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% | — |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 78% |
Multimodal reasoning MMMU-ProA tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 75.3% |
Multimodal MMMUTests the AI on understanding images and text together across many college subjects. Higher is better. | — | 81.7% |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Mar 5 2026 | Apr 16 2026 |
| Access | Proprietary | Open Weight |
Which is better: GPT-5.4-Pro or Qwen3.6?
GPT-5.4-Pro leads Qwen3.6 on 1 of the 1 benchmark they both report (GPQA Diamond). GPT-5.4-Pro shipped 42 days before Qwen3.6, so benchmark comparisons should account for the intervening progress.
GPT-5.4-Pro is proprietary, while Qwen3.6 is open weight.
On GPQA Diamond, GPT-5.4-Pro leads at 94.4% vs Qwen3.6 at 86%.
Frequently asked questions
GPT-5.4-Pro was released by OpenAI on Mar 5 2026.
Qwen3.6 was released by Qwen on Apr 16 2026.
GPT-5.4-Pro leads on GPQA Diamond — GPT-5.4-Pro 94.4% vs Qwen3.6 86%.
GPT-5.4-Pro is a proprietary model released by OpenAI. Qwen3.6 is an open weight model released by Qwen.
Other comparisons
GPT-5.4-ProvsClaude Opus 5Qwen3.6vsClaude Opus 5GPT-5.4-ProvsGemini 3.6 FlashQwen3.6vsGemini 3.6 FlashGPT-5.4-ProvsMuse Spark 1.1Qwen3.6vsMuse Spark 1.1GPT-5.4-ProvsGrok 4.5Qwen3.6vsGrok 4.5GPT-5.4-ProvsDeepSeek-V4-Flash-0731Qwen3.6vsDeepSeek-V4-Flash-0731GPT-5.4-ProvsMistral Medium 3.5Qwen3.6vsMistral Medium 3.5