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. | 671B | 0.8B/2B/4B/9B |
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. | 128k | 256k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.25SiliconFlow | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.00SiliconFlow | — |
| $100SiliconFlow · fp8 | — | |
| 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. | 49.2% | 65.6% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 68.4% | 81.7% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 81.2% | 82.5% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 91.5% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 59.4% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | — | 64.5% |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | — | 41.8% |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 73% |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 70.1% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 78.4% |
| Overview | ||
| Company | DeepSeek | Qwen |
| Release date | Mar 24 2025 | Mar 2 2026 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V3-0324vsClaude Fable 5.2Qwen3.5 SmallvsClaude Fable 5.2DeepSeek V3-0324vsGPT-6.2 AstraQwen3.5 SmallvsGPT-6.2 AstraDeepSeek V3-0324vsGemini 4 NeonQwen3.5 SmallvsGemini 4 NeonDeepSeek V3-0324vsMuse EmberQwen3.5 SmallvsMuse EmberDeepSeek V3-0324vsGrok 4.7Qwen3.5 SmallvsGrok 4.7DeepSeek V3-0324vsMistral Large 4Qwen3.5 SmallvsMistral Large 4Frequently asked questions
Qwen3.5 Small leads DeepSeek V3-0324 on 3 of the 3 benchmarks they both report (LiveCodeBench, GPQA Diamond, MMLU-Pro). DeepSeek V3-0324 shipped 343 days before Qwen3.5 Small, so benchmark comparisons should account for the intervening progress.
DeepSeek V3-0324 has 671B parameters, while Qwen3.5 Small has 0.8B/2B/4B/9B. Context windows are 128k (DeepSeek V3-0324) vs 256k (Qwen3.5 Small).
On LiveCodeBench, Qwen3.5 Small leads at 65.6% vs DeepSeek V3-0324 at 49.2%. On GPQA Diamond, Qwen3.5 Small leads at 81.7% vs DeepSeek V3-0324 at 68.4%. On MMLU-Pro, Qwen3.5 Small leads at 82.5% vs DeepSeek V3-0324 at 81.2%.