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 | — |
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% | 74.8% |
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% | 79% |
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% | — |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity'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. | — | 11% |
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% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 83% |
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 | SpaceXSI |
| Release date | Jan 26 2026 | Feb 17 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Qwen3-Max-ThinkingvsClaude Fable 5.2Grok 3 minivsClaude Fable 5.2Qwen3-Max-ThinkingvsGPT-6.2 AstraGrok 3 minivsGPT-6.2 AstraQwen3-Max-ThinkingvsGemini 4 NeonGrok 3 minivsGemini 4 NeonQwen3-Max-ThinkingvsMuse EmberGrok 3 minivsMuse EmberQwen3-Max-ThinkingvsDeepSeek-V4.1-Flash-1017Grok 3 minivsDeepSeek-V4.1-Flash-1017Qwen3-Max-ThinkingvsMistral Large 4Grok 3 minivsMistral Large 4Frequently asked questions
Qwen3-Max-Thinking leads Grok 3 mini on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Grok 3 mini shipped 343 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Qwen3-Max-Thinking) vs 128k (Grok 3 mini).
On LiveCodeBench, Qwen3-Max-Thinking leads at 85.9% vs Grok 3 mini at 74.8%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs Grok 3 mini at 79%.