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. | 200k | 256k |
| Benchmarks | ||
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. | 49.3% | 75.3% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 77.2% | 87.4% |
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% |
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. | 97.6% | — |
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% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 97.9% | — |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | 80.6 | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 70.9% |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 13.8% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 85.7% |
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. | 86.9% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 92% | — |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Jan 31 2025 | Jan 26 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
o3-mini-highvsClaude Fable 5.2Qwen3-Max-ThinkingvsClaude Fable 5.2o3-mini-highvsGemini 4 NeonQwen3-Max-ThinkingvsGemini 4 Neono3-mini-highvsMuse EmberQwen3-Max-ThinkingvsMuse Embero3-mini-highvsGrok 4.7Qwen3-Max-ThinkingvsGrok 4.7o3-mini-highvsDeepSeek-V4.1-Flash-1017Qwen3-Max-ThinkingvsDeepSeek-V4.1-Flash-1017o3-mini-highvsMistral Large 4Qwen3-Max-ThinkingvsMistral Large 4Frequently asked questions
Qwen3-Max-Thinking leads o3-mini-high on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). o3-mini-high shipped 360 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (o3-mini-high) vs 256k (Qwen3-Max-Thinking).
On SWE-Bench Verified, Qwen3-Max-Thinking leads at 75.3% vs o3-mini-high at 49.3%. On GPQA Diamond, Qwen3-Max-Thinking leads at 87.4% vs o3-mini-high at 77.2%.