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. | 1M | 256k |
| 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. | 71.9% | — |
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 | 58.5% | — |
HellaSwagReasoning — commonsense completion of short scenarios | 92.5% | — |
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. | 81.9% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 88.73% | — |
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. | 91.7% | — |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 52.1% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 58.5% | — |
| Overview | ||
| Company | Qwen | |
| Release date | Feb 15 2024 | Apr 14 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Gemini 1.5 ProvsClaude Fable 5.2Qwen3.6-Max-PreviewvsClaude Fable 5.2Gemini 1.5 ProvsGPT-6.2 AstraQwen3.6-Max-PreviewvsGPT-6.2 AstraGemini 1.5 ProvsMuse EmberQwen3.6-Max-PreviewvsMuse EmberGemini 1.5 ProvsGrok 4.7Qwen3.6-Max-PreviewvsGrok 4.7Gemini 1.5 ProvsDeepSeek-V4.1-Flash-1017Qwen3.6-Max-PreviewvsDeepSeek-V4.1-Flash-1017Gemini 1.5 ProvsMistral Large 4Qwen3.6-Max-PreviewvsMistral Large 4Frequently asked questions
Gemini 1.5 Pro and Qwen3.6-Max-Preview don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Gemini 1.5 Pro shipped 789 days before Qwen3.6-Max-Preview, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Gemini 1.5 Pro) vs 256k (Qwen3.6-Max-Preview).
Direct benchmark comparisons are unavailable — Gemini 1.5 Pro and Qwen3.6-Max-Preview don't publish scores on any of the same benchmarks.