GPT-4vsQwen3.5
GPT-4 | Qwen3.5 | |
|---|---|---|
| Specifications | ||
Parameters | — | 397B |
Context window | 8k | 1M |
| 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. | — | 76.4% |
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. | — | 69.3% |
Function synthesis HumanEval164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 67% | — |
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. | — | 52.5% |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | — | 69% |
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. | — | 28.7% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 88.4% |
General knowledge MMLUA 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 86.4% | — |
Grade-school math GSM8KGrade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | 92% | — |
Agentic computer use OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | — | 62.2% |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 80.8% |
Multimodal reasoning MMMU-ProA tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 79% |
Multimodal MMMUTests the AI on understanding images and text together across many college subjects. Higher is better. | — | 85% |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Mar 14 2023 | Feb 16 2026 |
| Access | Proprietary | Open Weight |
Which is better: GPT-4 or Qwen3.5?
GPT-4 and Qwen3.5 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. GPT-4 shipped 1070 days before Qwen3.5, so benchmark comparisons should account for the intervening progress.
Context windows are 8k (GPT-4) vs 1M (Qwen3.5). GPT-4 is proprietary, while Qwen3.5 is open weight.
Direct benchmark comparisons are unavailable — GPT-4 and Qwen3.5 don't publish scores on any of the same benchmarks.
Frequently asked questions
GPT-4 was released by OpenAI on Mar 14 2023.
Qwen3.5 was released by Qwen on Feb 16 2026.
GPT-4 has a 8k context window; Qwen3.5 has 1M.
GPT-4 is a proprietary model released by OpenAI. Qwen3.5 is an open weight model released by Qwen.