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. | — | 671B |
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. | 200k | 128k |
| 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. | 46% | — |
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. | 33.4% | — |
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. | — | 65.2% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 59.4% | — |
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. | — | 87.1% |
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. | — | 89.3% |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Jun 20 2024 | Dec 25 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude 3.5 SonnetvsGPT-6.1 SolDeepSeek V3 BasevsGPT-6.1 SolClaude 3.5 SonnetvsGemini 4 ArgonDeepSeek V3 BasevsGemini 4 ArgonClaude 3.5 SonnetvsMuse Spark OpenDeepSeek V3 BasevsMuse Spark OpenClaude 3.5 SonnetvsGrok 4.7DeepSeek V3 BasevsGrok 4.7Claude 3.5 SonnetvsMistral Large 4DeepSeek V3 BasevsMistral Large 4Claude 3.5 SonnetvsKimi K3DeepSeek V3 BasevsKimi K3Frequently asked questions
Claude 3.5 Sonnet and DeepSeek V3 Base don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude 3.5 Sonnet shipped 188 days before DeepSeek V3 Base, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude 3.5 Sonnet) vs 128k (DeepSeek V3 Base). Claude 3.5 Sonnet is closed, while DeepSeek V3 Base is open weight.
Direct benchmark comparisons are unavailable — Claude 3.5 Sonnet and DeepSeek V3 Base don't publish scores on any of the same benchmarks.