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. | 7B | 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. | 4k | 256k |
| These models have no shared benchmark scores. | ||
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% |
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 | 51.7% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 92.3% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 81.1% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 84.4% |
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. | 88.2% | — |
| Overview | ||
| Company | DeepSeek | Qwen |
| Release date | Feb 5 2024 | Jul 21 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-MathvsClaude Fable 5.2Qwen3-2507vsClaude Fable 5.2DeepSeek-MathvsGPT-6.2 AstraQwen3-2507vsGPT-6.2 AstraDeepSeek-MathvsGemini 4 NeonQwen3-2507vsGemini 4 NeonDeepSeek-MathvsMuse EmberQwen3-2507vsMuse EmberDeepSeek-MathvsGrok 4.7Qwen3-2507vsGrok 4.7DeepSeek-MathvsMistral Large 4Qwen3-2507vsMistral Large 4Frequently asked questions
DeepSeek-Math and Qwen3-2507 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek-Math shipped 532 days before Qwen3-2507, so benchmark comparisons should account for the intervening progress.
DeepSeek-Math has 7B parameters, while Qwen3-2507 has 4B/30B/235B. Context windows are 4k (DeepSeek-Math) vs 256k (Qwen3-2507).
Direct benchmark comparisons are unavailable — DeepSeek-Math and Qwen3-2507 don't publish scores on any of the same benchmarks.