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. | 16B | — |
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. | 32k | 256k |
| 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. | — | 79% |
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. | 57.3% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 43% |
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. | — | 25.4% |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | — | 38.6% |
MATHReasoning — accuracy on the original competition mathematics test set | 27.9% | — |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 91.7% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 87.5% |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 55.7% | — |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | 72% | — |
| Overview | ||
| Company | DeepSeek | SpaceXSI |
| Release date | May 16 2024 | Jul 9 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek V2 LitevsClaude Fable 5.2Grok 4vsClaude Fable 5.2DeepSeek V2 LitevsGPT-6.2 AstraGrok 4vsGPT-6.2 AstraDeepSeek V2 LitevsGemini 4 HydrogenGrok 4vsGemini 4 HydrogenDeepSeek V2 LitevsMuse EmberGrok 4vsMuse EmberDeepSeek V2 LitevsMistral Large 4Grok 4vsMistral Large 4DeepSeek V2 LitevsKimi K3.1 ProGrok 4vsKimi K3.1 ProFrequently asked questions
DeepSeek V2 Lite and Grok 4 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V2 Lite shipped 419 days before Grok 4, so benchmark comparisons should account for the intervening progress.
Context windows are 32k (DeepSeek V2 Lite) vs 256k (Grok 4). DeepSeek V2 Lite is open weight, while Grok 4 is closed.
Direct benchmark comparisons are unavailable — DeepSeek V2 Lite and Grok 4 don't publish scores on any of the same benchmarks.