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. | 0.8B/2B/4B/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 | 2M |
| 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. | 65.6% | 80% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 81.7% | 85.7% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 91.5% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 44.9% |
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. | — | 20% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 92% |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | 64.5% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 82.5% | — |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 41.8% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 73% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 70.1% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 78.4% | — |
| Overview | ||
| Company | Qwen | SpaceXSI |
| Release date | Mar 2 2026 | Sep 19 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Qwen3.5 SmallvsClaude Fable 5.2Grok 4 FastvsClaude Fable 5.2Qwen3.5 SmallvsGPT-6.2 AstraGrok 4 FastvsGPT-6.2 AstraQwen3.5 SmallvsGemini 4 NeonGrok 4 FastvsGemini 4 NeonQwen3.5 SmallvsMuse EmberGrok 4 FastvsMuse EmberQwen3.5 SmallvsDeepSeek-V4.1-Flash-1017Grok 4 FastvsDeepSeek-V4.1-Flash-1017Qwen3.5 SmallvsMistral Large 4Grok 4 FastvsMistral Large 4Frequently asked questions
Grok 4 Fast leads Qwen3.5 Small on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Grok 4 Fast shipped 164 days before Qwen3.5 Small, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Qwen3.5 Small) vs 2M (Grok 4 Fast). Qwen3.5 Small is open weight, while Grok 4 Fast is closed.
On LiveCodeBench, Grok 4 Fast leads at 80% vs Qwen3.5 Small at 65.6%. On GPQA Diamond, Grok 4 Fast leads at 85.7% vs Qwen3.5 Small at 81.7%.