Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 0.5B/1.5B/7B/57B/72B | >1T |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 128k | 256k |
| Benchmarks | ||
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 64.4% | 85.7% |
SWE-Bench VerifiedCoding — Real 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. | — | 75.3% |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | — | 85.9% |
HumanEvalFunction synthesis — 164 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. | 86% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | — | 30.2% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity'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. | — | 49.8% |
MATHReasoning — accuracy on the original competition mathematics test set | 69% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 87.4% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 70.9% |
MMLUGeneral knowledge — A 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. | 82.3% | — |
GSM8KGrade-school math — Grade-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. | 91.1% | — |
| Overview | ||
| Company | Qwen | Qwen |
| Release date | Jun 6 2024 | Jan 26 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Qwen2vsClaude Fable 5.2Qwen3-Max-ThinkingvsClaude Fable 5.2Qwen2vsGPT-6.2 AstraQwen3-Max-ThinkingvsGPT-6.2 AstraQwen2vsGemini 4 NeonQwen3-Max-ThinkingvsGemini 4 NeonQwen2vsMuse EmberQwen3-Max-ThinkingvsMuse EmberQwen2vsGrok 4.7Qwen3-Max-ThinkingvsGrok 4.7Qwen2vsDeepSeek-V4.1-Flash-1017Qwen3-Max-ThinkingvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen3-Max-Thinking leads Qwen2 on 1 of the 1 benchmark they both report (MMLU-Pro). Qwen2 shipped 599 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.
Qwen2 has 0.5B/1.5B/7B/57B/72B parameters, while Qwen3-Max-Thinking has >1T. Context windows are 128k (Qwen2) vs 256k (Qwen3-Max-Thinking). Qwen2 is open weight, while Qwen3-Max-Thinking is closed.
On MMLU-Pro, Qwen3-Max-Thinking leads at 85.7% vs Qwen2 at 64.4%.