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 |
| Benchmarks | ||
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. | 19% | 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. | 39.7% | 35.1% |
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% |
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. | 87.2% | — |
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 | Jul 24 2024 | Dec 11 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek Coder V2-0724vsClaude Fable 5.2Gemini 2.0 FlashvsClaude Fable 5.2DeepSeek Coder V2-0724vsGPT-6.2 AstraGemini 2.0 FlashvsGPT-6.2 AstraDeepSeek Coder V2-0724vsMuse EmberGemini 2.0 FlashvsMuse EmberDeepSeek Coder V2-0724vsGrok 4.7Gemini 2.0 FlashvsGrok 4.7DeepSeek Coder V2-0724vsMistral Large 4Gemini 2.0 FlashvsMistral Large 4DeepSeek Coder V2-0724vsKimi K3.1 ProGemini 2.0 FlashvsKimi K3.1 ProFrequently asked questions
DeepSeek Coder V2-0724 and Gemini 2.0 Flash are evenly matched across the 2 benchmarks they both report (SWE-Bench Verified, LiveCodeBench). DeepSeek Coder V2-0724 shipped 140 days before Gemini 2.0 Flash, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (DeepSeek Coder V2-0724) vs 1M (Gemini 2.0 Flash). DeepSeek Coder V2-0724 is open weight, while Gemini 2.0 Flash is closed.
On SWE-Bench Verified, Gemini 2.0 Flash leads at 21.4% vs DeepSeek Coder V2-0724 at 19%. On LiveCodeBench, DeepSeek Coder V2-0724 leads at 39.7% vs Gemini 2.0 Flash at 35.1%.