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. | 1.6T | — |
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. | 1M | 1M |
| 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. | $0.90Relace | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $1.50Relace | — |
| $255Relace · fp4 | — | |
| Benchmarks | ||
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. | 14% | 15% |
CheatBenchCheating rate — Measures how often AI agents try to cheat on difficult assignments, such as reading hidden answers, copying work or manipulating grading. The overall score gives equal weight to ten categories; the sycophancy category measures how far an agent shifts its beliefs toward a user's stated views. Scores describe each model in its tested agent setup, and task success is measured separately. Lower is better. | 75.1% | — |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 21.4% |
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. | 93.5% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 83.4% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 90.1% | — |
| Overview | ||
| Company | DeepSeek | |
| Release date | Apr 24 2026 | Dec 11 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-ProvsClaude Haiku 5.5Gemini 2.0 FlashvsClaude Haiku 5.5DeepSeek-V4-ProvsGPT-6.1 SolGemini 2.0 FlashvsGPT-6.1 SolDeepSeek-V4-ProvsMuse Spark OpenGemini 2.0 FlashvsMuse Spark OpenDeepSeek-V4-ProvsGrok 4.7Gemini 2.0 FlashvsGrok 4.7DeepSeek-V4-ProvsMistral Large 4Gemini 2.0 FlashvsMistral Large 4DeepSeek-V4-ProvsKimi K3Gemini 2.0 FlashvsKimi K3Frequently asked questions
Gemini 2.0 Flash leads DeepSeek-V4-Pro on 1 of the 1 benchmark they both report (BullshitBench v2). Gemini 2.0 Flash shipped 499 days before DeepSeek-V4-Pro, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (DeepSeek-V4-Pro) vs 1M (Gemini 2.0 Flash). DeepSeek-V4-Pro is open weight, while Gemini 2.0 Flash is closed.
On BullshitBench v2, Gemini 2.0 Flash leads at 15% vs DeepSeek-V4-Pro at 14%.