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 | 2M |
| These models have no shared benchmark scores. | ||
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. | — | 80% |
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% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 44.9% |
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. | — | 20% |
MATHReasoning — accuracy on the original competition mathematics test set | 71.02% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 92% |
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 | SpaceXSI |
| Release date | Jun 28 2024 | Sep 19 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek V2-0628vsClaude Fable 5.2Grok 4 FastvsClaude Fable 5.2DeepSeek V2-0628vsGPT-6.2 AstraGrok 4 FastvsGPT-6.2 AstraDeepSeek V2-0628vsGemini 4 HydrogenGrok 4 FastvsGemini 4 HydrogenDeepSeek V2-0628vsMuse EmberGrok 4 FastvsMuse EmberDeepSeek V2-0628vsMistral Large 4Grok 4 FastvsMistral Large 4DeepSeek V2-0628vsKimi K3.1 ProGrok 4 FastvsKimi K3.1 ProFrequently asked questions
DeepSeek V2-0628 and Grok 4 Fast don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V2-0628 shipped 448 days before Grok 4 Fast, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (DeepSeek V2-0628) vs 2M (Grok 4 Fast). DeepSeek V2-0628 is open weight, while Grok 4 Fast is closed.
Direct benchmark comparisons are unavailable — DeepSeek V2-0628 and Grok 4 Fast don't publish scores on any of the same benchmarks.