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 | — |
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 | 1M |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.30 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $2.50 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.03 |
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. | — | $0.15Google AI Studio |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $1.25Google AI Studio |
| — | $185Google list price | |
| 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. | 88.7% | 63.5% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | 96% | 78% |
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% | 78.3% |
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. | — | 19% |
Aider Polyglot (diff)Coding — editing code in six languages using the diff edit format | — | 44.2% |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | — | 12.1% |
Humanity's Last Exam · text only, no toolsMultidisciplinary reasoning — accuracy on the 2,158 text-only questions without tools | 30.6% | — |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | — | 29.7% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 76.7% |
| Overview | ||
| Company | DeepSeek | |
| Release date | Dec 1 2025 | Apr 17 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek-V3.2-SpecialevsClaude Fable 5.2Gemini 2.5 FlashvsClaude Fable 5.2DeepSeek-V3.2-SpecialevsGPT-6.2 AstraGemini 2.5 FlashvsGPT-6.2 AstraDeepSeek-V3.2-SpecialevsMuse EmberGemini 2.5 FlashvsMuse EmberDeepSeek-V3.2-SpecialevsGrok 4.7Gemini 2.5 FlashvsGrok 4.7DeepSeek-V3.2-SpecialevsMistral Large 4Gemini 2.5 FlashvsMistral Large 4DeepSeek-V3.2-SpecialevsKimi K3.1 ProGemini 2.5 FlashvsKimi K3.1 ProFrequently asked questions
DeepSeek-V3.2-Speciale leads Gemini 2.5 Flash on 3 of the 3 benchmarks they both report (LiveCodeBench, AIME 2025, GPQA Diamond). Only Gemini 2.5 Flash has a verified first-party price for an available API: $0.30 per million input tokens and $2.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek-V3.2-Speciale. Gemini 2.5 Flash shipped 228 days before DeepSeek-V3.2-Speciale, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (DeepSeek-V3.2-Speciale) vs 1M (Gemini 2.5 Flash). DeepSeek-V3.2-Speciale is open weight, while Gemini 2.5 Flash is closed.
On LiveCodeBench, DeepSeek-V3.2-Speciale leads at 88.7% vs Gemini 2.5 Flash at 63.5%. On AIME 2025, DeepSeek-V3.2-Speciale leads at 96% vs Gemini 2.5 Flash at 78%. On GPQA Diamond, DeepSeek-V3.2-Speciale leads at 85.7% vs Gemini 2.5 Flash at 78.3%.