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 | 200k |
| Overview | ||
| Company | DeepSeek | OpenAI |
| Release date | Sep 5 2024 | May 16 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek V2.5vsClaude Fable 5.2codex-mini-latestvsClaude Fable 5.2DeepSeek V2.5vsGemini 4 Carboncodex-mini-latestvsGemini 4 CarbonDeepSeek V2.5vsMuse Embercodex-mini-latestvsMuse EmberDeepSeek V2.5vsGrok 4.7codex-mini-latestvsGrok 4.7DeepSeek V2.5vsMistral Large 4codex-mini-latestvsMistral Large 4DeepSeek V2.5vsKimi K3.1 Procodex-mini-latestvsKimi K3.1 ProFrequently asked questions
DeepSeek V2.5 and codex-mini-latest don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V2.5 shipped 253 days before codex-mini-latest, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (DeepSeek V2.5) vs 200k (codex-mini-latest). DeepSeek V2.5 is open weight, while codex-mini-latest is closed.
Direct benchmark comparisons are unavailable — DeepSeek V2.5 and codex-mini-latest don't publish scores on any of the same benchmarks.