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. | >1T | 9B |
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. | 256k | 128k |
| Benchmarks | ||
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% | 28.5% |
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% | — |
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. | — | 82.3% |
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% | — |
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% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 85.7% | — |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Jan 26 2026 | Jul 5 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Qwen3-Max-ThinkingvsClaude Fable 5.2CodeGeeX4-ALL-9BvsClaude Fable 5.2Qwen3-Max-ThinkingvsGPT-6.2 AstraCodeGeeX4-ALL-9BvsGPT-6.2 AstraQwen3-Max-ThinkingvsGemini 4 NeonCodeGeeX4-ALL-9BvsGemini 4 NeonQwen3-Max-ThinkingvsMuse EmberCodeGeeX4-ALL-9BvsMuse EmberQwen3-Max-ThinkingvsGrok 4.7CodeGeeX4-ALL-9BvsGrok 4.7Qwen3-Max-ThinkingvsDeepSeek-V4.1-Flash-1017CodeGeeX4-ALL-9BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen3-Max-Thinking leads CodeGeeX4-ALL-9B on 1 of the 1 benchmark they both report (LiveCodeBench). CodeGeeX4-ALL-9B shipped 570 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.
Qwen3-Max-Thinking has >1T parameters, while CodeGeeX4-ALL-9B has 9B. Context windows are 256k (Qwen3-Max-Thinking) vs 128k (CodeGeeX4-ALL-9B). Qwen3-Max-Thinking is closed, while CodeGeeX4-ALL-9B is open weight.
On LiveCodeBench, Qwen3-Max-Thinking leads at 85.9% vs CodeGeeX4-ALL-9B at 28.5%.