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. | 2M | 256k |
| 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. | 36% | 74.1% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 64.7% | 81.1% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 79.1% | 84.4% |
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% |
MATHReasoning — accuracy on the original competition mathematics test set | 91.8% | — |
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 | 44.3% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 72.7% | — |
| Overview | ||
| Company | Qwen | |
| Release date | Feb 5 2025 | Jul 21 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Gemini 2.0 ProvsClaude Fable 5.2Qwen3-2507vsClaude Fable 5.2Gemini 2.0 ProvsGPT-6.2 AstraQwen3-2507vsGPT-6.2 AstraGemini 2.0 ProvsMuse EmberQwen3-2507vsMuse EmberGemini 2.0 ProvsGrok 4.7Qwen3-2507vsGrok 4.7Gemini 2.0 ProvsDeepSeek-V4.1-Flash-1017Qwen3-2507vsDeepSeek-V4.1-Flash-1017Gemini 2.0 ProvsMistral Large 4Qwen3-2507vsMistral Large 4Frequently asked questions
Qwen3-2507 leads Gemini 2.0 Pro on 3 of the 3 benchmarks they both report (LiveCodeBench, GPQA Diamond, MMLU-Pro). Gemini 2.0 Pro shipped 166 days before Qwen3-2507, so benchmark comparisons should account for the intervening progress.
Context windows are 2M (Gemini 2.0 Pro) vs 256k (Qwen3-2507). Gemini 2.0 Pro is closed, while Qwen3-2507 is open weight.
On LiveCodeBench, Qwen3-2507 leads at 74.1% vs Gemini 2.0 Pro at 36%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs Gemini 2.0 Pro at 64.7%. On MMLU-Pro, Qwen3-2507 leads at 84.4% vs Gemini 2.0 Pro at 79.1%.