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. | 236B | — |
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 |
| 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. | — | 15% |
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. | — | 35.1% |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 84.76% | — |
MATHReasoning — accuracy on the original competition mathematics test set | 71.02% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 62.1% |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | — | 76.4% |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | — | 70.7% |
| Overview | ||
| Company | DeepSeek | |
| Release date | Jun 28 2024 | Dec 11 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek V2-0628vsClaude Fable 5.2Gemini 2.0 FlashvsClaude Fable 5.2DeepSeek V2-0628vsGPT-6.2 AstraGemini 2.0 FlashvsGPT-6.2 AstraDeepSeek V2-0628vsMuse EmberGemini 2.0 FlashvsMuse EmberDeepSeek V2-0628vsGrok 4.7Gemini 2.0 FlashvsGrok 4.7DeepSeek V2-0628vsMistral Large 4Gemini 2.0 FlashvsMistral Large 4DeepSeek V2-0628vsKimi K3.1 ProGemini 2.0 FlashvsKimi K3.1 ProFrequently asked questions
DeepSeek V2-0628 and Gemini 2.0 Flash don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V2-0628 shipped 166 days before Gemini 2.0 Flash, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (DeepSeek V2-0628) vs 1M (Gemini 2.0 Flash). DeepSeek V2-0628 is open weight, while Gemini 2.0 Flash is closed.
Direct benchmark comparisons are unavailable — DeepSeek V2-0628 and Gemini 2.0 Flash don't publish scores on any of the same benchmarks.