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. | 200k | 128k |
| These models have no shared benchmark scores. | ||
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. | 49% | — |
| Overview | ||
| Company | Anthropic | DeepSeek |
| Release date | Oct 22 2024 | Dec 10 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Claude 3.5 Sonnet (upgraded)vsGPT-6.1 SolDeepSeek V2.5 (Revised)vsGPT-6.1 SolClaude 3.5 Sonnet (upgraded)vsGemini 4 ArgonDeepSeek V2.5 (Revised)vsGemini 4 ArgonClaude 3.5 Sonnet (upgraded)vsMuse Spark OpenDeepSeek V2.5 (Revised)vsMuse Spark OpenClaude 3.5 Sonnet (upgraded)vsGrok 4.7DeepSeek V2.5 (Revised)vsGrok 4.7Claude 3.5 Sonnet (upgraded)vsMistral Large 4DeepSeek V2.5 (Revised)vsMistral Large 4Claude 3.5 Sonnet (upgraded)vsKimi K3DeepSeek V2.5 (Revised)vsKimi K3Frequently asked questions
Claude 3.5 Sonnet (upgraded) and DeepSeek V2.5 (Revised) don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude 3.5 Sonnet (upgraded) shipped 49 days before DeepSeek V2.5 (Revised), so benchmark comparisons should account for the intervening progress.
Context windows are 200k (Claude 3.5 Sonnet (upgraded)) vs 128k (DeepSeek V2.5 (Revised)). Claude 3.5 Sonnet (upgraded) is closed, while DeepSeek V2.5 (Revised) is open weight.
Direct benchmark comparisons are unavailable — Claude 3.5 Sonnet (upgraded) and DeepSeek V2.5 (Revised) don't publish scores on any of the same benchmarks.