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 | 480B |
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. | — | $0.35Venice |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $1.50Venice |
| — | $145Venice · fp8 | |
| These models have no shared benchmark scores. | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 20% |
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. | 88.7% | — |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 30.6% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 96% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 85.7% | — |
| Overview | ||
| Company | DeepSeek | Qwen |
| Release date | Dec 1 2025 | Jul 22 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek-V3.2-SpecialevsClaude Fable 5.2Qwen3-CodervsClaude Fable 5.2DeepSeek-V3.2-SpecialevsGPT-6.2 AstraQwen3-CodervsGPT-6.2 AstraDeepSeek-V3.2-SpecialevsGemini 4 HydrogenQwen3-CodervsGemini 4 HydrogenDeepSeek-V3.2-SpecialevsMuse EmberQwen3-CodervsMuse EmberDeepSeek-V3.2-SpecialevsGrok 4.7Qwen3-CodervsGrok 4.7DeepSeek-V3.2-SpecialevsMistral Large 4Qwen3-CodervsMistral Large 4Frequently asked questions
DeepSeek-V3.2-Speciale and Qwen3-Coder don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen3-Coder shipped 132 days before DeepSeek-V3.2-Speciale, so benchmark comparisons should account for the intervening progress.
DeepSeek-V3.2-Speciale has 671B parameters, while Qwen3-Coder has 480B. Context windows are 128k (DeepSeek-V3.2-Speciale) vs 256k (Qwen3-Coder).
Direct benchmark comparisons are unavailable — DeepSeek-V3.2-Speciale and Qwen3-Coder don't publish scores on any of the same benchmarks.