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. | — | 4B/30B/235B |
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 | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 74.9% | 81.1% |
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. | — | 74.1% |
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. | 96.3% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 87.8% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | — | 18.2% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 97.3% | — |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | 79.2 | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 92.3% |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 13.4% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 84.4% |
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. | 85.9% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 90.8% | — |
| Overview | ||
| Company | OpenAI | Qwen |
| Release date | Jan 31 2025 | Jul 21 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
o3-minivsClaude Fable 5.2Qwen3-2507vsClaude Fable 5.2o3-minivsGemini 4 NeonQwen3-2507vsGemini 4 Neono3-minivsMuse EmberQwen3-2507vsMuse Embero3-minivsGrok 4.7Qwen3-2507vsGrok 4.7o3-minivsDeepSeek-V4.1-Flash-1017Qwen3-2507vsDeepSeek-V4.1-Flash-1017o3-minivsMistral Large 4Qwen3-2507vsMistral Large 4Frequently asked questions
Qwen3-2507 leads o3-mini on 1 of the 1 benchmark they both report (GPQA Diamond). o3-mini shipped 171 days before Qwen3-2507, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (o3-mini) vs 256k (Qwen3-2507). o3-mini is closed, while Qwen3-2507 is open weight.
On GPQA Diamond, Qwen3-2507 leads at 81.1% vs o3-mini at 74.9%.