Compare AI models
| Specifications | ||
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 |
| These models have no shared benchmark scores. | ||
NL2Repo-BenchRepo-level code generation — Tests whether the AI can turn a natural-language requirement into working code across an entire repository, not just produce a single function or patch. Higher is better. | 42.9% | — |
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. | — | 88.4% |
Terminal-Bench 2.0Agentic terminal coding — Can 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. | 65.4% | — |
MATHReasoning — accuracy on the original competition mathematics test set | — | 76.1% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 75.5% |
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. | — | 87.5% |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | — | 69% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 66.1% |
| Overview | ||
| Company | Qwen | SpaceXSI |
| Release date | Apr 14 2026 | Aug 13 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Qwen3.6-Max-PreviewvsClaude Fable 5.2Grok‑2vsClaude Fable 5.2Qwen3.6-Max-PreviewvsGPT-6.2 AstraGrok‑2vsGPT-6.2 AstraQwen3.6-Max-PreviewvsGemini 4 NeonGrok‑2vsGemini 4 NeonQwen3.6-Max-PreviewvsMuse EmberGrok‑2vsMuse EmberQwen3.6-Max-PreviewvsDeepSeek-V4.1-Flash-1017Grok‑2vsDeepSeek-V4.1-Flash-1017Qwen3.6-Max-PreviewvsMistral Large 4Grok‑2vsMistral Large 4Frequently asked questions
Qwen3.6-Max-Preview and Grok‑2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Grok‑2 shipped 609 days before Qwen3.6-Max-Preview, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Qwen3.6-Max-Preview) vs 128k (Grok‑2).
Direct benchmark comparisons are unavailable — Qwen3.6-Max-Preview and Grok‑2 don't publish scores on any of the same benchmarks.